Torbjørn Karl Svendsen
About
For a complete CV, please use the link above ("CV")
Torbjørn Svendsen (1955) is a Professor at the Department of Electronic Systems. Professor Svendsen holds a MScEE, and a PhD both from the NTNU. He is an ISCA Fellow and IEEE Life Senior Member.
Fields of interest and present research activities
My research interests have from the outset in 1979 been speech signal processing. The first period was focused on source coding, i.e. speech compression, which was also the subject of my doctoral thesis. From the mid 80’s the research interests have been mainly on automatic speech recognition, but also areas like spoken dialogue systems and speech synthesis have been included in my research. Speech analysis methods and lexical modelling, e.g. pronunciation modelling have been two central areas. Realizing that current approaches to speech recognition seem to be nearing a saturation point in terms of performance, a major recent activity has been to investigate new paradigms for speech recognition, aiming to integrate phonetic and linguistic knowledge in a statistical framework based on detection of (language universal) phonetic features. Lately, the challenges of reliable recognition of children's speech and transcription of conversational, accented and dialectal speech have been central in my research.
Work experience
- NTNU (1979-1981 Research assistant, 1983-1984 doctoral fellowship, 1988-1995 Associate professor, 1995-present Professor), Director NTNU Digital (2015-2021)
- SINTEF (1981-1987, Research scientist)
- Research visits at AT&T Bell Labs, Murray Hill, NJ (1986-1987, 1990); Griffith University, Brisbane, Australia (1996-97); AT&T Labs, Florham Park, NJ (2000); Queensland University of Technology, Brisbane, Australia (2002-03); Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA (2013); Delft University of Technology (2022); Kore University of Enna, Italy (2023)
Professional merits
Peer review and professional evaluation work:
- Reviewer for international journals like IEEE Transactions (Communications; Signal Processing; Audio, Speech and Language Processing; Multimedia); EURASIP Journal on Applied Signal Processing, Signal, Image and Video Processing; and Speech Communication, and various conferences and workshops on speech and signal processing.
- Member of Speech Communication journal Editorial Board
- Reviewer for EU's Language Engineering program and the Information Society Research Programme of the Academy of Finland. Project reviews for the Norwegian, Australian, Swiss, Dutch, Belgian and South African Research Councils
- Opponent/member of examination boards for 26 doctoral theses
Membership in academic and professional committees
- Various appointments at the national level, e.g. in the Research Council of Norway, incl. grant committee member for the IKTPLUSS program, program board chair for the VERDIKT program, and in the Norwegian Language Council.
- Member of advisory board, Norwegian Language Bank (“Språkbanken”)
- Member of Technical committees, Eurospeech2001 and Interspeech2012, and organizing committee of Eurospeech2001.
- Life Senior Member, IEEE
- Member, Signal Processing Society Speech Technical Committee (1998-2001)
- Elected member, Norwegian Academy of Technological Sciences
- ISCA Fellow
- Board of International Speech Communication Association (ISCA) (Member 2015-2017, Vice President 2017-2021, Board Secretary 2021-2023)
Other professional merits
- Project manager, "Atomic Units for Language Universal Speech" (current), "Spoken dialog systems for telephony"; "Speech interfaces and reasoning systems"; "Norwegian corpus for language technology"; “Voice centric user interfaces for location based services”; “Tools for realistic speech synthesis in”; “Spoken Information Retrieval by Knowledge Utilization in Statistical Speech Processing”; “Rundkast – A transcribed broadcast news for applications in language technology”(past projects).
- Vice chair, COST action 278; WG chair COST actions 232 and 249; Advisory Scientific Board member, EU project ACORNS; Board member, Nordic Graduate School of Language Technology (former actions and activities)
- Previous NTNU appointments: Department Head, Department of Telecommunications; Vice Dean, Faculty of Electrical Engineering and Telecommunications; member of several NTNU committees
- 19 PhD students graduated (3 as co-supervisor). Currently supervising 5 PhD students.
- ~100 Master degree students graduated
- >100 papers in international journals and conferences
Research
My research interests have from the outset in 1979 been speech signal processing. The first period was focused on source coding, i.e. speech compression, which was also the subject of my doctoral thesis. From the mid 80’s the research interests have been mainly on automatic speech recognition, but also areas like spoken dialogue systems and speech synthesis have been included in my research. Speech analysis methods and lexical modelling, e.g. pronunciation modelling have been two central areas. Realizing that current approaches to speech recognition seem to be nearing a saturation point in terms of performance, a major recent activity has been to investigate new paradigms for speech recognition, aiming to integrate phonetic and linguistic knowledge in a statistical framework based on detection of (language universal) phonetic features. Lately, the challenges of reliable recognition of children's speech and transcription of conversational, accented and dialectal speech have been central in my research.
Publications
2024
-
Olstad, Anne Marte Haug;
Smolander, Anna;
Strömbergsson, Sofia;
Ylinen, Sari;
Lehtonen, Minna;
Kurimo, Mikko.
(2024)
Collecting Linguistic Resources for Assessing Children’s Pronunciation of Nordic Languages.
Proceedings of LREC
Academic article
-
Cao, Xinwei;
Fan, Zijian;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2024)
A Framework for Phoneme-Level Pronunciation Assessment Using CTC.
Interspeech
Academic article
-
La Quatra, Moreno;
Turco, Maria Francesca;
Svendsen, Torbjørn Karl;
Salvi, Giampiero;
Orozco-Arroyave, Juan Rafael;
Siniscalchi, Sabato Marco.
(2024)
Exploiting Foundation Models and Speech Enhancement for Parkinson’s Disease Detection from Speech in Real-World Operative Conditions.
Interspeech
Academic article
-
Fan, Zijian;
Cao, Xinwei;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2024)
Towards Better Recognition of Spontaneous Children's Speech: Speaker-Clustering Fine-Tuning of Whisper.
Machine Learning for Signal Processing
Academic article
2023
-
Parsons, Phoebe;
Kvale, Knut;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2023)
A character-based analysis of impacts of dialects on end-to-end Norwegian ASR.
University of Tartu
Academic chapter/article/Conference paper
-
Getman, Yaroslav;
Phan, Nhan;
Al-Ghezi, Ragheb;
Voskoboinik, Ekaterina;
Singh, Mittul;
Grosz, Tamas.
(2023)
Developing an AI-Assisted Low-Resource Spoken Language Learning App for Children.
IEEE Access
Academic article
-
Rugayan, Janine Lizbeth Cabrera;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2023)
Perceptual and Task-Oriented Assessment of a Semantic Metric for ASR Evaluation.
Interspeech (USB)
Academic article
-
Cao, Xinwei;
Fan, Zijian;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2023)
An Analysis of Goodness of Pronunciation for Child Speech.
Interspeech
Academic article
-
Gelderblom, Femke Berre;
Myrvoll, Tor Andre;
Svendsen, Torbjørn Karl.
(2023)
Evaluating Performance Metrics for Deep Neural Network-based Speech Enhancement Systems.
Doctoral theses at NTNU (53)
Doctoral dissertation
-
Solberg, Per Erik;
Ortiz Cabello, Pablo;
Parsons, Phoebe;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2023)
Improving Generalization of Norwegian ASR with Limited Linguistic Resources.
University of Tartu
Academic chapter/article/Conference paper
-
Gelderblom, Femke Berre;
Tronstad, Tron Vedul;
Svendsen, Torbjørn Karl;
Myrvoll, Tor Andre.
(2023)
On the Predictive Power of Objective Intelligibility Metrics for the Subjective Performance of Deep Complex Convolutional Recurrent Speech Enhancement Networks.
IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)
Academic article
-
Fan, Zijian;
Cao, Xinwei;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2023)
Using Modified Adult Speech as Data Augmentation for Child Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Academic article
2022
-
Rugayan, Janine Lizbeth Cabrera;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2022)
Semantically Meaningful Metrics for Norwegian ASR Systems.
Interspeech (USB)
Academic article
-
Getman, Yaroslav;
Al-Ghezi, Ragheb;
Voskoboinik, Ekaterina;
Grósz, Tamás;
Kurimo, Mikko;
Salvi, Giampiero.
(2022)
wav2vec2-based Speech Rating System for Children with Speech Sound Disorder.
Interspeech (USB)
Academic article
-
Kvale, Knut;
Gulla, Jon Atle;
Adde, Line;
Solberg, Per Erik;
Svendsen, Torbjørn Karl;
Moshagen, Sjur Nørstebø.
(2022)
Taleteknologi og kunstig intelligens.
Teknologirådet
Report
2021
-
Sabzi Shahrebabaki, Abdolreza;
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn Karl.
(2021)
Raw Speech-to-Articulatory Inversion by Temporal Filtering and Decimation.
Interspeech
Academic article
-
Sabzi Shahrebabaki, Abdolreza;
Salvi, Giampiero;
Svendsen, Torbjørn Karl;
Siniscalchi, Sabato Marco.
(2021)
Acoustic-to-Articulatory Mapping With Joint Optimization of Deep Speech Enhancement and Articulatory Inversion Models.
IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)
Academic article
-
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Imran, Ali Shariq;
Johnsen, Magne Hallstein;
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn Karl.
(2021)
A Two-Stage Deep Modeling Approach to Articulatory Inversion.
IEEE (Institute of Electrical and Electronics Engineers)
Academic chapter/article/Conference paper
-
Sabzi Shahrebabaki, Abdolreza;
Siniscalchi, Sabato Marco;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2021)
A DNN Based Speech Enhancement Approach to Noise Robust Acoustic-to-Articulatory Inversion.
IEEE (Institute of Electrical and Electronics Engineers)
Academic chapter/article/Conference paper
2020
-
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Siniscalchi, Sabato Marco;
Salvi, Giampiero;
Svendsen, Torbjørn.
(2020)
Transfer learning of articulatory information through phone information.
Interspeech (USB)
Academic article
-
Sabzi Shahrebabaki, Abdolreza;
Siniscalchi, Marco;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2020)
Sequence-to-sequence articulatory inversion through time convolution of sub-band frequency signals.
Interspeech (USB)
Academic article
2019
-
Imran, Ali Shariq;
Haflan, Vetle;
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Svendsen, Torbjørn Karl.
(2019)
Evaluating Acoustic Feature Maps in 2D-CNN for Speaker Identification.
Association for Computing Machinery (ACM)
Academic chapter/article/Conference paper
-
Imran, Ali Shariq;
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Svendsen, Torbjørn Karl.
(2019)
A Study on the Performance Evaluation of Machine Learning Models for Phoneme Classification.
Association for Computing Machinery (ACM)
Academic chapter/article/Conference paper
-
Sabzi Shahrebabaki, Abdolreza;
Imran, Ali Shariq;
Olfati, Negar;
Svendsen, Torbjørn Karl.
(2019)
A Comparative Study of Deep Learning Techniques on Frame-Level Speech Data Classification.
Circuits, systems, and signal processing
Academic article
-
Imran, Ali Shariq;
Kastrati, Zenun;
Svendsen, Torbjørn Karl;
Kurti, Arianit.
(2019)
Text-Independent Speaker ID for Automatic Video Lecture Classification Using Deep Learning.
Association for Computing Machinery (ACM)
Academic chapter/article/Conference paper
-
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Imran, Ali Shariq;
Sabato Marco, Siniscalchi;
Svendsen, Torbjørn Karl.
(2019)
A Phonetic-Level Analysis of Different Input Features for Articulatory Inversion.
Interspeech (USB)
Academic article
2018
-
Sabzi Shahrebabaki, Abdolreza;
Imran, Ali Shariq;
Olfati, Negar;
Svendsen, Torbjørn Karl.
(2018)
Acoustic Feature Comparison for Different Speaking Rates.
Springer
Academic chapter/article/Conference paper
2015
-
Svendsen, Torbjørn Karl;
Hamar, Jarle Bauck.
(2015)
Combining NdHMM and Phonetic Feature Detection for Speech Recognition.
Academic chapter/article/Conference paper
-
Næss, Arild Brandrud;
Svendsen, Torbjørn Karl;
Livescu, Karen.
(2015)
Nearest Neighbor Frame Classification for Articulatory Speech Recognition.
Norges teknisk-naturvitenskapelige universitet
Doktoravhandlinger ved NTNU (24)
Doctoral dissertation
2014
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2014)
An artificial neural network approach to automatic speech processing.
Neurocomputing
Academic article
-
Soufifar, Mehdi;
Svendsen, Torbjørn;
Burget, Lukas.
(2014)
Subspace Modeling of Discrete features for Language Recognition.
NTNU-trykk
Doctoral dissertation
2013
-
Hamar, Jarle Bauck;
Doddipatla, Rama Sanand;
Svendsen, Torbjørn;
Sreenivas, Thippur.
(2013)
Non-Negative Durational HMM.
IEEE Signal Processing Society
Academic chapter/article/Conference paper
-
Doddipatla, Rama Sanand;
Svendsen, Torbjørn.
(2013)
Synthetic Speaker Models Using VTLN to Improve the Performance of Children in Mismatched Speaker Conditions for ASR.
Interspeech (USB)
Academic article
2012
-
Svendsen, Torbjørn.
(2012)
Data med barnestemme.
Forskning.no
Interview Journal
-
Siniscalchi, Sabato Marco;
Reed, Jeremy;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2012)
Universal attribute characterization of spoken languages for automatic spoken language recognition.
Computer Speech and Language
Academic article
-
Siniscalchi, Sabato Marco;
Lyu, DC;
Svendsen, Torbjørn;
Lee, CH.
(2012)
Experiments on Cross-Language Attribute Detection and Phone Recognition With Minimal Target-Specific Training Data.
IEEE Transactions on Audio, Speech, and Language Processing
Academic article
2011
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2011)
A Bottom-Up Stepwise Knowledge-Integration Approach to Large Vocabulary Continuous Speech Recognition Using Weighted Finite State Machines.
Interspeech
Academic article
-
Skogstad, Trond;
Svendsen, Torbjørn.
(2011)
Frequency-Warped and Stabilized Time-Varying Cepstral Coefficients.
Interspeech
Academic article
-
Adde, Line;
Svendsen, Torbjørn.
(2011)
Pronunciation Variation Modeling of Non-Natie Proper Names by Discriminative Tree Search.
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Academic article
-
Soufifar, Mehdi;
Kockmann, Marcel;
Burget, Lukas;
Plchot, Oldrich;
Glembek, Ondrej;
Svendsen, Torbjørn.
(2011)
iVector Approach to Phonotactic Language Recognition.
Interspeech
Academic article
-
Kvale, Knut;
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Lyse, Gunn Inger;
Gjesdal, Anje Müller.
(2011)
Datamaskinen må skjønne norsk.
Bergens Tidende
Feature article
2010
-
Adde, Line;
Svendsen, Torbjørn.
(2010)
A Comparative Analysis of Discriminative and Non-Discriminative Pronunciation Priors in Pronunciation Variation Modeling.
IEEE Signal Processing Society
Other
-
Saeidi, Rahim;
Soufifar, Mehdi;
Kinnunen, Tomi;
Svendsen, Torbjørn;
Fränti, Pasi.
(2010)
UEF-NTNU System Description for Albayzin 2010 Language Recognition Evaluation.
Other
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2010)
A Survey on Recent Progress in the ASAT/SIRKUS Paradigm.
IEEE conference proceedings
Other
-
Adde, Line;
Svendsen, Torbjørn.
(2010)
NameDat: A Database of English Proper Names Spoken by Native Norwegians.
European Language Resources Association
Academic chapter/article/Conference paper
-
Sikveland, Rein Ove;
Öttl, Anton;
Amdal, Ingunn;
Ernestus, Mirjam;
Svendsen, Torbjørn;
Edlund, Jens.
(2010)
Spontal-N: A Corpus of Interactional Spoken Norwegian.
European Language Resources Association
Other
-
Adde, Line;
Reveil, Bert;
Martens, Jean-Pierre;
Svendsen, Torbjørn.
(2010)
A Minimum Classification Error Approach to Pronunciation Variation Modeling of Non-Native Proper Names.
Interspeech
Academic article
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Sorbello, Filippo;
Lee, Chin-Hui.
(2010)
Experimental Studies on Continuous Speech Recognition Using Neural Architectures with ‘Adaptive’ Hidden Activation Functions.
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Academic article
-
Siniscalchi, Sabato Marco;
Reed, Jeremy;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2010)
Exploiting Context-Dependency and Acoustic Resolution of Universal Speech Attribute Models in Spoken Language Recognition.
Interspeech
Academic article
-
Skogstad, Trond;
Svendsen, Torbjørn.
(2010)
Intra-Frame Variability As a Predictor of Frame Classifiability.
Interspeech
Academic article
2009
-
Siniscalchi, Sabato Marco;
Reed, Jeremy;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2009)
Exploring Universal Attribute Characterization of Spoken Languages for Spoken Language Recognition.
Interspeech
Academic article
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2009)
A Phonetic Feature Based Lattice Rescoring Approach to LVCSR.
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Academic article
-
Mertens, Timo Pascal;
Schneider, Daniel;
Næss, Arild Brandrud;
Svendsen, Torbjørn.
(2009)
Lexicon Adaptation for Subword Speech Recognition.
IEEE Signal Processing Society
Academic chapter/article/Conference paper
2008
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
lee, chin-hui.
(2008)
A Penalized Logistic Regression Approach to Detection Based Phone Classification.
Interspeech
Academic article
-
Amdal, Ingunn;
Strand, Ole Morten;
Almberg, Jørn;
Svendsen, Torbjørn.
(2008)
RUNDKAST: An Annotated Norwegian Broadcast News Speech Corpus.
European Language Resources Association
Academic chapter/article/Conference paper
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
lee, chin-hui.
(2008)
Toward a Detector-Based Universal Phone Recognizer.
Other
-
Skogstad, Trond;
Svendsen, Torbjørn.
(2008)
Time-Varying Cepstral Coefficients.
Other
-
Siniscalchi, Sabato Marco;
Birkenes, Øystein;
Johnsen, Magne Hallstein;
Svendsen, Torbjørn.
(2008)
Joint Optimization of Event Detectors and Evidence Merger for Continuous Speech Recognition.
Other
2007
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2007)
Towards Bottom-Up Continuous Phone Recognition.
IEEE Signal Processing Society
Academic chapter/article/Conference paper
2006
-
Amdal, Ingunn;
Svendsen, Torbjørn.
(2006)
FonDat1: A Speech Synthesis Corpus for Norwegian.
European Language Resources Association
Academic chapter/article/Conference paper
-
Amdal, Ingunn;
Johnsen, Magne Hallstein;
Svendsen, Torbjørn.
(2006)
Log Likelihood Ratio Based Annotation Verification of a Norwegian Speech Synthesis Database.
IEEE conference proceedings
Academic chapter/article/Conference paper
2005
-
Amdal, Ingunn;
Svendsen, Torbjørn.
(2005)
Unit Selection Synthesis Database Development Using Utterance Verification.
Eurospeech : Proceedings of the European Conference on Speech Communication and Technology
Academic article
-
Svendsen, Torbjørn;
Amdal, Ingunn;
Bjørkan, Ingmund;
Meen, Dyre;
Heggtveit, Per Olav;
Natvig, Jon Emil.
(2005)
FONEMA - Tools for realistic speech synthesis in Norwegian.
Tapir Akademisk Forlag
Academic chapter/article/Conference paper
-
Meen, Dyre;
Svendsen, Torbjørn;
Natvig, Jon-Emil.
(2005)
Improving Phone Label Alignment Accuracy by Utilizing Voicing Information.
Academic chapter/article/Conference paper
-
Svendsen, Torbjørn;
Egeberg, Andreas;
Holter, Trym;
Skogstad, Trond.
(2005)
VOCALS - Voice centric user interfaces for location based services.
Tapir Akademisk Forlag
Academic chapter/article/Conference paper
-
Bjørkan, Ingmund;
Svendsen, Torbjørn;
Farner, Snorre.
(2005)
Comparing Spectral Distance Measures for Join Cost Optimization in Concatenative Speech Synthesis.
Eurospeech : Proceedings of the European Conference on Speech Communication and Technology
Academic article
-
Bjørkan, Ingmund;
Svendsen, Torbjørn.
(2005)
Comparing Spectral Distance Measures for Join Cost Optmization.
Eurospeech : Proceedings of the European Conference on Speech Communication and Technology
Academic article
-
Skogstad, Trond;
Svendsen, Torbjørn.
(2005)
Distributed ASR Using Speech Coder Data for Efficient Feature Vector Representation.
Eurospeech : Proceedings of the European Conference on Speech Communication and Technology
Academic article
2004
-
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Harborg, Erik;
Kvale, Knut.
(2004)
Language Technology Towards 2020.
Academic chapter/article/Conference paper
2003
-
Svendsen, Torbjørn.
(2003)
Speech Technology: Past, Present and Future.
Telektronikk
Academic article
2002
-
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Natvig, Jon Emil.
(2002)
Talsmann talesyntese som hjelpemiddel for dyslektikere.
Telenor Communication AS
Report
-
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Breivik, Torbjørg.
(2002)
Samling og tilgjengeleggjering av norske språkteknologiressursar.
Norsk språkråd
Report
-
Svendsen, Torbjørn.
(2002)
Roles for Speech And Language Technology in The Information Society.
Tampere University Press
Academic chapter/article/Conference paper
2001
-
Svendsen, Torbjørn.
(2001)
Nordisk forskningssamarbeid innen språkteknologi.
Språknytt
Popular scientific article
2000
-
Foldvik, Arne Kjell;
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Thygesen, Ragnar.
(2000)
Dysleksi og språkteknologi.
Adresseavisen
Feature article
-
Amdal, Ingunn;
Holter, Trym;
Svendsen, Torbjørn.
(2000)
Modellering av uttalevariasjon for automatisk talegjenkjenning.
Nordlyd
Academic article
1999
-
Holter, Trym;
Svendsen, Torbjørn.
(1999)
Maximum likelihood modelling of pronunciation variation.
Speech Communication
Academic article
-
Svendsen, Torbjørn.
(1999)
Taleteknologi.
Språk i Norden
Academic article
-
Svendsen, Torbjørn;
Johnsen, Magne Hallstein;
Nordgård, Torbjørn;
Hofland, Knut;
Hofland, Knut;
Ore, Christian Emil.
(1999)
Nasjonalt korpus for språkteknologi - forprosjekt.
Norges forskningsråd
Norges forskningsråd
Report
1998
-
Svendsen, Torbjørn.
(1998)
Blir norsk gresk for språkteknologien?.
Språknytt
Academic article
1995
-
Harborg, Erik;
Johnsen, Magne Hallstein;
Svendsen, Torbjørn.
(1995)
Talegjenkjenning for teksting av direktesendte programmer - en studie.
SINTEF DELAB
Report
-
Harborg, Erik;
Johnsen, Magne Hallstein;
Svendsen, Torbjørn.
(1995)
Talegjenkjenning II.
SINTEF DELAB
Report
1994
-
Svendsen, Torbjørn.
(1994)
Talebaserte brukergrensesnitt.
NORSIGnalet : organ for NORSIG, Norsk forening for signalbehandling
Popular scientific article
Journal publications
-
Olstad, Anne Marte Haug;
Smolander, Anna;
Strömbergsson, Sofia;
Ylinen, Sari;
Lehtonen, Minna;
Kurimo, Mikko.
(2024)
Collecting Linguistic Resources for Assessing Children’s Pronunciation of Nordic Languages.
Proceedings of LREC
Academic article
-
Cao, Xinwei;
Fan, Zijian;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2024)
A Framework for Phoneme-Level Pronunciation Assessment Using CTC.
Interspeech
Academic article
-
La Quatra, Moreno;
Turco, Maria Francesca;
Svendsen, Torbjørn Karl;
Salvi, Giampiero;
Orozco-Arroyave, Juan Rafael;
Siniscalchi, Sabato Marco.
(2024)
Exploiting Foundation Models and Speech Enhancement for Parkinson’s Disease Detection from Speech in Real-World Operative Conditions.
Interspeech
Academic article
-
Fan, Zijian;
Cao, Xinwei;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2024)
Towards Better Recognition of Spontaneous Children's Speech: Speaker-Clustering Fine-Tuning of Whisper.
Machine Learning for Signal Processing
Academic article
-
Getman, Yaroslav;
Phan, Nhan;
Al-Ghezi, Ragheb;
Voskoboinik, Ekaterina;
Singh, Mittul;
Grosz, Tamas.
(2023)
Developing an AI-Assisted Low-Resource Spoken Language Learning App for Children.
IEEE Access
Academic article
-
Rugayan, Janine Lizbeth Cabrera;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2023)
Perceptual and Task-Oriented Assessment of a Semantic Metric for ASR Evaluation.
Interspeech (USB)
Academic article
-
Cao, Xinwei;
Fan, Zijian;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2023)
An Analysis of Goodness of Pronunciation for Child Speech.
Interspeech
Academic article
-
Gelderblom, Femke Berre;
Tronstad, Tron Vedul;
Svendsen, Torbjørn Karl;
Myrvoll, Tor Andre.
(2023)
On the Predictive Power of Objective Intelligibility Metrics for the Subjective Performance of Deep Complex Convolutional Recurrent Speech Enhancement Networks.
IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)
Academic article
-
Fan, Zijian;
Cao, Xinwei;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2023)
Using Modified Adult Speech as Data Augmentation for Child Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Academic article
-
Rugayan, Janine Lizbeth Cabrera;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2022)
Semantically Meaningful Metrics for Norwegian ASR Systems.
Interspeech (USB)
Academic article
-
Getman, Yaroslav;
Al-Ghezi, Ragheb;
Voskoboinik, Ekaterina;
Grósz, Tamás;
Kurimo, Mikko;
Salvi, Giampiero.
(2022)
wav2vec2-based Speech Rating System for Children with Speech Sound Disorder.
Interspeech (USB)
Academic article
-
Sabzi Shahrebabaki, Abdolreza;
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn Karl.
(2021)
Raw Speech-to-Articulatory Inversion by Temporal Filtering and Decimation.
Interspeech
Academic article
-
Sabzi Shahrebabaki, Abdolreza;
Salvi, Giampiero;
Svendsen, Torbjørn Karl;
Siniscalchi, Sabato Marco.
(2021)
Acoustic-to-Articulatory Mapping With Joint Optimization of Deep Speech Enhancement and Articulatory Inversion Models.
IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)
Academic article
-
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Siniscalchi, Sabato Marco;
Salvi, Giampiero;
Svendsen, Torbjørn.
(2020)
Transfer learning of articulatory information through phone information.
Interspeech (USB)
Academic article
-
Sabzi Shahrebabaki, Abdolreza;
Siniscalchi, Marco;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2020)
Sequence-to-sequence articulatory inversion through time convolution of sub-band frequency signals.
Interspeech (USB)
Academic article
-
Sabzi Shahrebabaki, Abdolreza;
Imran, Ali Shariq;
Olfati, Negar;
Svendsen, Torbjørn Karl.
(2019)
A Comparative Study of Deep Learning Techniques on Frame-Level Speech Data Classification.
Circuits, systems, and signal processing
Academic article
-
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Imran, Ali Shariq;
Sabato Marco, Siniscalchi;
Svendsen, Torbjørn Karl.
(2019)
A Phonetic-Level Analysis of Different Input Features for Articulatory Inversion.
Interspeech (USB)
Academic article
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2014)
An artificial neural network approach to automatic speech processing.
Neurocomputing
Academic article
-
Doddipatla, Rama Sanand;
Svendsen, Torbjørn.
(2013)
Synthetic Speaker Models Using VTLN to Improve the Performance of Children in Mismatched Speaker Conditions for ASR.
Interspeech (USB)
Academic article
-
Svendsen, Torbjørn.
(2012)
Data med barnestemme.
Forskning.no
Interview Journal
-
Siniscalchi, Sabato Marco;
Reed, Jeremy;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2012)
Universal attribute characterization of spoken languages for automatic spoken language recognition.
Computer Speech and Language
Academic article
-
Siniscalchi, Sabato Marco;
Lyu, DC;
Svendsen, Torbjørn;
Lee, CH.
(2012)
Experiments on Cross-Language Attribute Detection and Phone Recognition With Minimal Target-Specific Training Data.
IEEE Transactions on Audio, Speech, and Language Processing
Academic article
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2011)
A Bottom-Up Stepwise Knowledge-Integration Approach to Large Vocabulary Continuous Speech Recognition Using Weighted Finite State Machines.
Interspeech
Academic article
-
Skogstad, Trond;
Svendsen, Torbjørn.
(2011)
Frequency-Warped and Stabilized Time-Varying Cepstral Coefficients.
Interspeech
Academic article
-
Adde, Line;
Svendsen, Torbjørn.
(2011)
Pronunciation Variation Modeling of Non-Natie Proper Names by Discriminative Tree Search.
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Academic article
-
Soufifar, Mehdi;
Kockmann, Marcel;
Burget, Lukas;
Plchot, Oldrich;
Glembek, Ondrej;
Svendsen, Torbjørn.
(2011)
iVector Approach to Phonotactic Language Recognition.
Interspeech
Academic article
-
Kvale, Knut;
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Lyse, Gunn Inger;
Gjesdal, Anje Müller.
(2011)
Datamaskinen må skjønne norsk.
Bergens Tidende
Feature article
-
Adde, Line;
Reveil, Bert;
Martens, Jean-Pierre;
Svendsen, Torbjørn.
(2010)
A Minimum Classification Error Approach to Pronunciation Variation Modeling of Non-Native Proper Names.
Interspeech
Academic article
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Sorbello, Filippo;
Lee, Chin-Hui.
(2010)
Experimental Studies on Continuous Speech Recognition Using Neural Architectures with ‘Adaptive’ Hidden Activation Functions.
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Academic article
-
Siniscalchi, Sabato Marco;
Reed, Jeremy;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2010)
Exploiting Context-Dependency and Acoustic Resolution of Universal Speech Attribute Models in Spoken Language Recognition.
Interspeech
Academic article
-
Skogstad, Trond;
Svendsen, Torbjørn.
(2010)
Intra-Frame Variability As a Predictor of Frame Classifiability.
Interspeech
Academic article
-
Siniscalchi, Sabato Marco;
Reed, Jeremy;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2009)
Exploring Universal Attribute Characterization of Spoken Languages for Spoken Language Recognition.
Interspeech
Academic article
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2009)
A Phonetic Feature Based Lattice Rescoring Approach to LVCSR.
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
Academic article
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
lee, chin-hui.
(2008)
A Penalized Logistic Regression Approach to Detection Based Phone Classification.
Interspeech
Academic article
-
Amdal, Ingunn;
Svendsen, Torbjørn.
(2005)
Unit Selection Synthesis Database Development Using Utterance Verification.
Eurospeech : Proceedings of the European Conference on Speech Communication and Technology
Academic article
-
Bjørkan, Ingmund;
Svendsen, Torbjørn;
Farner, Snorre.
(2005)
Comparing Spectral Distance Measures for Join Cost Optimization in Concatenative Speech Synthesis.
Eurospeech : Proceedings of the European Conference on Speech Communication and Technology
Academic article
-
Bjørkan, Ingmund;
Svendsen, Torbjørn.
(2005)
Comparing Spectral Distance Measures for Join Cost Optmization.
Eurospeech : Proceedings of the European Conference on Speech Communication and Technology
Academic article
-
Skogstad, Trond;
Svendsen, Torbjørn.
(2005)
Distributed ASR Using Speech Coder Data for Efficient Feature Vector Representation.
Eurospeech : Proceedings of the European Conference on Speech Communication and Technology
Academic article
-
Svendsen, Torbjørn.
(2003)
Speech Technology: Past, Present and Future.
Telektronikk
Academic article
-
Svendsen, Torbjørn.
(2001)
Nordisk forskningssamarbeid innen språkteknologi.
Språknytt
Popular scientific article
-
Foldvik, Arne Kjell;
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Thygesen, Ragnar.
(2000)
Dysleksi og språkteknologi.
Adresseavisen
Feature article
-
Amdal, Ingunn;
Holter, Trym;
Svendsen, Torbjørn.
(2000)
Modellering av uttalevariasjon for automatisk talegjenkjenning.
Nordlyd
Academic article
-
Holter, Trym;
Svendsen, Torbjørn.
(1999)
Maximum likelihood modelling of pronunciation variation.
Speech Communication
Academic article
-
Svendsen, Torbjørn.
(1999)
Taleteknologi.
Språk i Norden
Academic article
-
Svendsen, Torbjørn.
(1998)
Blir norsk gresk for språkteknologien?.
Språknytt
Academic article
-
Svendsen, Torbjørn.
(1994)
Talebaserte brukergrensesnitt.
NORSIGnalet : organ for NORSIG, Norsk forening for signalbehandling
Popular scientific article
Part of book/report
-
Parsons, Phoebe;
Kvale, Knut;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2023)
A character-based analysis of impacts of dialects on end-to-end Norwegian ASR.
University of Tartu
Academic chapter/article/Conference paper
-
Solberg, Per Erik;
Ortiz Cabello, Pablo;
Parsons, Phoebe;
Svendsen, Torbjørn Karl;
Salvi, Giampiero.
(2023)
Improving Generalization of Norwegian ASR with Limited Linguistic Resources.
University of Tartu
Academic chapter/article/Conference paper
-
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Imran, Ali Shariq;
Johnsen, Magne Hallstein;
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn Karl.
(2021)
A Two-Stage Deep Modeling Approach to Articulatory Inversion.
IEEE (Institute of Electrical and Electronics Engineers)
Academic chapter/article/Conference paper
-
Sabzi Shahrebabaki, Abdolreza;
Siniscalchi, Sabato Marco;
Salvi, Giampiero;
Svendsen, Torbjørn Karl.
(2021)
A DNN Based Speech Enhancement Approach to Noise Robust Acoustic-to-Articulatory Inversion.
IEEE (Institute of Electrical and Electronics Engineers)
Academic chapter/article/Conference paper
-
Imran, Ali Shariq;
Haflan, Vetle;
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Svendsen, Torbjørn Karl.
(2019)
Evaluating Acoustic Feature Maps in 2D-CNN for Speaker Identification.
Association for Computing Machinery (ACM)
Academic chapter/article/Conference paper
-
Imran, Ali Shariq;
Sabzi Shahrebabaki, Abdolreza;
Olfati, Negar;
Svendsen, Torbjørn Karl.
(2019)
A Study on the Performance Evaluation of Machine Learning Models for Phoneme Classification.
Association for Computing Machinery (ACM)
Academic chapter/article/Conference paper
-
Imran, Ali Shariq;
Kastrati, Zenun;
Svendsen, Torbjørn Karl;
Kurti, Arianit.
(2019)
Text-Independent Speaker ID for Automatic Video Lecture Classification Using Deep Learning.
Association for Computing Machinery (ACM)
Academic chapter/article/Conference paper
-
Sabzi Shahrebabaki, Abdolreza;
Imran, Ali Shariq;
Olfati, Negar;
Svendsen, Torbjørn Karl.
(2018)
Acoustic Feature Comparison for Different Speaking Rates.
Springer
Academic chapter/article/Conference paper
-
Svendsen, Torbjørn Karl;
Hamar, Jarle Bauck.
(2015)
Combining NdHMM and Phonetic Feature Detection for Speech Recognition.
Academic chapter/article/Conference paper
-
Hamar, Jarle Bauck;
Doddipatla, Rama Sanand;
Svendsen, Torbjørn;
Sreenivas, Thippur.
(2013)
Non-Negative Durational HMM.
IEEE Signal Processing Society
Academic chapter/article/Conference paper
-
Adde, Line;
Svendsen, Torbjørn.
(2010)
A Comparative Analysis of Discriminative and Non-Discriminative Pronunciation Priors in Pronunciation Variation Modeling.
IEEE Signal Processing Society
Other
-
Saeidi, Rahim;
Soufifar, Mehdi;
Kinnunen, Tomi;
Svendsen, Torbjørn;
Fränti, Pasi.
(2010)
UEF-NTNU System Description for Albayzin 2010 Language Recognition Evaluation.
Other
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2010)
A Survey on Recent Progress in the ASAT/SIRKUS Paradigm.
IEEE conference proceedings
Other
-
Adde, Line;
Svendsen, Torbjørn.
(2010)
NameDat: A Database of English Proper Names Spoken by Native Norwegians.
European Language Resources Association
Academic chapter/article/Conference paper
-
Sikveland, Rein Ove;
Öttl, Anton;
Amdal, Ingunn;
Ernestus, Mirjam;
Svendsen, Torbjørn;
Edlund, Jens.
(2010)
Spontal-N: A Corpus of Interactional Spoken Norwegian.
European Language Resources Association
Other
-
Mertens, Timo Pascal;
Schneider, Daniel;
Næss, Arild Brandrud;
Svendsen, Torbjørn.
(2009)
Lexicon Adaptation for Subword Speech Recognition.
IEEE Signal Processing Society
Academic chapter/article/Conference paper
-
Amdal, Ingunn;
Strand, Ole Morten;
Almberg, Jørn;
Svendsen, Torbjørn.
(2008)
RUNDKAST: An Annotated Norwegian Broadcast News Speech Corpus.
European Language Resources Association
Academic chapter/article/Conference paper
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
lee, chin-hui.
(2008)
Toward a Detector-Based Universal Phone Recognizer.
Other
-
Skogstad, Trond;
Svendsen, Torbjørn.
(2008)
Time-Varying Cepstral Coefficients.
Other
-
Siniscalchi, Sabato Marco;
Birkenes, Øystein;
Johnsen, Magne Hallstein;
Svendsen, Torbjørn.
(2008)
Joint Optimization of Event Detectors and Evidence Merger for Continuous Speech Recognition.
Other
-
Siniscalchi, Sabato Marco;
Svendsen, Torbjørn;
Lee, Chin-Hui.
(2007)
Towards Bottom-Up Continuous Phone Recognition.
IEEE Signal Processing Society
Academic chapter/article/Conference paper
-
Amdal, Ingunn;
Svendsen, Torbjørn.
(2006)
FonDat1: A Speech Synthesis Corpus for Norwegian.
European Language Resources Association
Academic chapter/article/Conference paper
-
Amdal, Ingunn;
Johnsen, Magne Hallstein;
Svendsen, Torbjørn.
(2006)
Log Likelihood Ratio Based Annotation Verification of a Norwegian Speech Synthesis Database.
IEEE conference proceedings
Academic chapter/article/Conference paper
-
Svendsen, Torbjørn;
Amdal, Ingunn;
Bjørkan, Ingmund;
Meen, Dyre;
Heggtveit, Per Olav;
Natvig, Jon Emil.
(2005)
FONEMA - Tools for realistic speech synthesis in Norwegian.
Tapir Akademisk Forlag
Academic chapter/article/Conference paper
-
Meen, Dyre;
Svendsen, Torbjørn;
Natvig, Jon-Emil.
(2005)
Improving Phone Label Alignment Accuracy by Utilizing Voicing Information.
Academic chapter/article/Conference paper
-
Svendsen, Torbjørn;
Egeberg, Andreas;
Holter, Trym;
Skogstad, Trond.
(2005)
VOCALS - Voice centric user interfaces for location based services.
Tapir Akademisk Forlag
Academic chapter/article/Conference paper
-
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Harborg, Erik;
Kvale, Knut.
(2004)
Language Technology Towards 2020.
Academic chapter/article/Conference paper
-
Svendsen, Torbjørn.
(2002)
Roles for Speech And Language Technology in The Information Society.
Tampere University Press
Academic chapter/article/Conference paper
Report
-
Gelderblom, Femke Berre;
Myrvoll, Tor Andre;
Svendsen, Torbjørn Karl.
(2023)
Evaluating Performance Metrics for Deep Neural Network-based Speech Enhancement Systems.
Doctoral theses at NTNU (53)
Doctoral dissertation
-
Kvale, Knut;
Gulla, Jon Atle;
Adde, Line;
Solberg, Per Erik;
Svendsen, Torbjørn Karl;
Moshagen, Sjur Nørstebø.
(2022)
Taleteknologi og kunstig intelligens.
Teknologirådet
Report
-
Næss, Arild Brandrud;
Svendsen, Torbjørn Karl;
Livescu, Karen.
(2015)
Nearest Neighbor Frame Classification for Articulatory Speech Recognition.
Norges teknisk-naturvitenskapelige universitet
Doktoravhandlinger ved NTNU (24)
Doctoral dissertation
-
Soufifar, Mehdi;
Svendsen, Torbjørn;
Burget, Lukas.
(2014)
Subspace Modeling of Discrete features for Language Recognition.
NTNU-trykk
Doctoral dissertation
-
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Natvig, Jon Emil.
(2002)
Talsmann talesyntese som hjelpemiddel for dyslektikere.
Telenor Communication AS
Report
-
Nordgård, Torbjørn;
Svendsen, Torbjørn;
Breivik, Torbjørg.
(2002)
Samling og tilgjengeleggjering av norske språkteknologiressursar.
Norsk språkråd
Report
-
Svendsen, Torbjørn;
Johnsen, Magne Hallstein;
Nordgård, Torbjørn;
Hofland, Knut;
Hofland, Knut;
Ore, Christian Emil.
(1999)
Nasjonalt korpus for språkteknologi - forprosjekt.
Norges forskningsråd
Norges forskningsråd
Report
-
Harborg, Erik;
Johnsen, Magne Hallstein;
Svendsen, Torbjørn.
(1995)
Talegjenkjenning for teksting av direktesendte programmer - en studie.
SINTEF DELAB
Report
-
Harborg, Erik;
Johnsen, Magne Hallstein;
Svendsen, Torbjørn.
(1995)
Talegjenkjenning II.
SINTEF DELAB
Report
Teaching
Courses
Knowledge Transfer
2024
-
Academic lectureParsons, Phoebe Luree Turner; Bremnes, Heming Strømholt; Kvale, Knut; Svendsen, Torbjørn Karl; Salvi, Giampiero. (2024) Norwegian dialect identification: is prosody enough?. Fonetik , Stockholm 2024-06-03 - 2024-06-05
-
LectureSvendsen, Torbjørn Karl. (2024) Kunstig intelligens - hva, hvorfor, hvordan. Hyllestad folkeakademi Folkeakademiet , Hyllestad kommunehus 2024-04-04 - 2024-04-04
-
LectureSvendsen, Torbjørn Karl. (2024) Machines may "think" - but can they master the spoken language?. NTNU IE Friday talk , Trondheim 2024-01-26 - 2024-01-26
-
LectureSvendsen, Torbjørn Karl. (2024) What is spoken language technology?. Universitetsbiblioteket From Toys to Tools to Terror(ist?) in a decade , Trondheim 2024-01-26 - 2024-01-26
-
Academic lectureCao, Xinwei; Fan, Zijian; Svendsen, Torbjørn Karl; Salvi, Giampiero. (2024) Framework for Phoneme-Level Pronunciation Assessment Using CTC. ISCA Interspeech , Kos, Greece 2024-09-01 - 2024-09-05
-
LectureSvendsen, Torbjørn Karl. (2024) Hva er kunstig intelligens? Muligheter for KI i eiendomsbransjen. Kjeldsberg AS Internseminar , Trondheim 2024-03-18 - 2024-03-18
-
Academic lectureFan, Zijian; Cao, Xinwei; Salvi, Giampiero; Svendsen, Torbjørn Karl. (2024) Towards Better Recognition of Spontaneous Children's Speech: Speaker-Clustering Fine-Tuning of Whisper. IEEE chine Learning for Signal Processing , London, UK 2024-09-22 - 2024-09-25
2023
-
Academic lectureSvendsen, Torbjørn Karl. (2023) Joint MAP of Direct and Indirect Adaptation. Symposium for Celebrating 40 Years of Bayesian Learning in Speech and Language Processing and Beyond , Taipei 2023-12-20 - 2023-12-20
-
Academic lectureSvendsen, Torbjørn Karl. (2023) Speech Signal Processing. Kore University of Enna Speech DSP , Enna 2023-03-22 - 2023-03-23
-
Academic lectureSvendsen, Torbjørn Karl. (2023) Combining direct and indirect adaptation for speech recognition. National Taiwan University Seminar on speech technology , National Taiwan University 2023-12-21 - 2023-12-21
-
Academic lectureRugayan, Janine Lizbeth Cabrera; Salvi, Giampiero; Svendsen, Torbjørn Karl. (2023) Perceptual and Task-Oriented Assessment of a Semantic Metric for ASR Evaluation. ISCA Interspeech , Dublin, Irland 2023-08-20 - 2023-08-24
-
Academic lectureParsons, Phoebe Luree Turner; Kvale, Knut; Svendsen, Torbjørn Karl; Salvi, Giampiero. (2023) A character-based analysis of impacts of dialects on end-to-end Norwegian ASR. ACL 24th Nordic Conference on Computational Linguistics (NoDaLiDa) , Tórshavn, Faroe Islands 2023-05-14 - 2023-05-18
-
Academic lectureFan, Zijian; Cao, Xinwei; Salvi, Giampiero; Svendsen, Torbjørn Karl. (2023) Using Modified Adult Speech as Data Augmentation for Child Speech Recognition. IEEE ICASSP , Rhodes, Greece 2023-06-04 - 2023-06-10
-
Academic lectureCao, Xinwei; Fan, Zijian; Svendsen, Torbjørn Karl; Salvi, Giampiero. (2023) An Analysis of Goodness of Pronunciation for Child Speech. ISCA Interspeech , Dublin, Irland 2023-08-20 - 2023-08-24
-
Academic lectureSolberg, Per Erik; Ortiz Cabello, Pablo; Parsons, Phoebe Luree Turner; Svendsen, Torbjørn Karl; Salvi, Giampiero. (2023) Improving Generalization of Norwegian ASR with Limited Linguistic Resources. ACL 24th Nordic Conference on Computational Linguistics (NoDaLiDa) , Tórshavn, Faroe Islands 2023-05-15 - 2023-05-18
2022
-
Academic lectureGetman, Yaroslav; Al-Ghezi, Ragheb; Voskoboinik, Ekaterina; Grósz, Tamás; Kurimo, Mikko; Salvi, Giampiero. (2022) wav2vec2-based Speech Rating System for Children with Speech Sound Disorder. ISCA Interspeech , Incheon, Korea 2022-09-18 - 2022-09-22
-
Academic lectureRugayan, Janine Lizbeth Cabrera; Svendsen, Torbjørn Karl; Salvi, Giampiero. (2022) Semantically Meaningful Metrics for Norwegian ASR Systems. ISCA Interspeech , Incheon, Korea 2022-09-18 - 2022-09-22
2018
-
Popular scientific lectureØien, Geir Egil Dahle; Mengshoel, Ole Jakob; Ramampiaro, Heri; Svendsen, Torbjørn Karl. (2018) NTNUs strategiske satsing på kunstig intelligens (AI) – bakgrunn, aktiviteter og fremtidsvyer. Det Kongelige Norske Vitenskapers Selskap Medlemsmøte, Det Kongelige Norske Vitenskapers Selskap , Trondheim 2018-11-12 - 2018-11-12
2011
-
Academic lectureSvendsen, Torbjørn. (2011) Universal Speech Attribute Characterization for Automatic Speech Recognition and Spoken Language Recognition. MIT CSAIL CSAIL Seminar , Boston 2011-12-05 - 2011-12-05
-
Popular scientific lectureSvendsen, Torbjørn. (2011) Hva er det med tale? Forskningsutfordringer og aktiviteter innen taleteknologi. MediaLT På snakkis med teknologien , Oslo 2011-11-09 - 2011-11-09
-
Academic lectureJavier Rodriguez-Fuentes, Luis; Penagarikano, Mikel; Varona, Amparo; Diez, Mireia; Bordel, German; Martinez, David. (2011) MULTI-SITE HETEROGENEOUS SYSTEM FUSIONS FOR THE ALBAYZIN 2010 LANGUAGE RECOGNITION EVALUATION. IEEE Automatic Speech Recognition and Understanding , Big Island, Hawaii 2011-12-11 - 2011-12-15
2010
-
Academic lectureAdde, Line; Svendsen, Torbjørn. (2010) A Comparative Analysis of Discriminative and Non-Discriminative Pronunciation Priors in Pronunciation Variation Modeling. IEEE IEEE Workshop on Spoken Language Technology 2010 , Berkeley, California 2010-12-12 - 2010-12-15
-
Academic lectureMeen, Dyre; Svendsen, Torbjørn. (2010) The NTNU Concatenative Speech Synthesizer. ISCA Blizzard Challenge Workshop , Kyoto 2010-09-25 - 2010-09-25
-
Academic lectureAdde, Line; Svendsen, Torbjørn. (2010) NameDat: A Database of English Proper Names Spoken by Native Norwegians. ELDA LREC , Valetta 2010-05-17 -
-
Academic lectureSiniscalchi, Sabato Marco; Svendsen, Torbjørn; Sorbello, Filippo; Lee, Chin-Hui. (2010) Experimental Studies on Continuous Speech Recognition Using Neural Architectures with ‘Adaptive’ Hidden Activation Functions. IEEE ICASSP 2010 , Dallas, Texas 2010-03-14 - 2010-03-19
-
Academic lectureSaeidi, Rahim; Soufifar, Mehdi; Kinnunen, Tomi; Svendsen, Torbjørn; Fränti, Pasi. (2010) UEF-NTNU System Description for Albayzin 2010 Language Recognition Evaluation. University of Vigo FALA 2010 , Vigo 2010-10-10 - 2010-10-12
-
Academic lectureSkogstad, Trond; Svendsen, Torbjørn. (2010) Intra-Frame Variability As a Predictor of Frame Classifiability. ISCA Interspeech 2010 , Makuhari 2010-09-27 - 2010-09-30
-
Academic lectureSikveland, Rein Ove; Öttl, Anton; Amdal, Ingunn; Ernestus, Mirjam; Svendsen, Torbjørn; Edlund, Jens. (2010) Spontal-N: A Corpus of Interactional Spoken Norwegian. ELDA LREC , Valetta 2010-05-17 - 2010-05-23
-
Academic lectureSiniscalchi, Sabato Marco; Reed, Jeremy; Svendsen, Torbjørn; Lee, Chin-Hui. (2010) Exploiting Context-Dependency and Acoustic Resolution of Universal Speech Attribute Models in Spoken Language Recognition. ISCA Interspeech 2010 , Makuhari 2010-09-27 - 2010-09-30
-
Academic lectureAdde, Line; Reveil, Bert; Martens, Jean-Pierre; Svendsen, Torbjørn. (2010) A Minimum Classification Error Approach to Pronunciation Variation Modeling of Non-Native Proper Names. ISCA Interspeech 2010 , Makuhari 2010-09-27 - 2010-09-30
-
Academic lectureSiniscalchi, Sabato Marco; Svendsen, Torbjørn; Lee, Chin-Hui. (2010) A Survey on Recent Progress in the ASAT/SIRKUS Paradigm. IEEE ISCSLP 2010 , Tainan 2010-11-21 - 2010-12-03
2009
-
InterviewSvendsen, Torbjørn. (2009) VERDIKT på Forskningsdagene. Nytt fra VERDIKT Nytt fra VERDIKT [Newspaper] 2009-11-03
-
InterviewSvendsen, Torbjørn. (2009) Språkteknologien gjør fremskritt igjen. forskning.no forskning.no [Internet] 2009-04-09
-
Academic lectureSiniscalchi, Sabato Marco; Svendsen, Torbjørn; Lee, Chin-Hui. (2009) A Phonetic Feature Based Lattice Rescoring Approach to LVCSR. IEEE IEEE International Conference on Acoustics, Speech and Signal Processing , Taipei 2009-04-19 - 2009-04-24
-
Academic lectureSiniscalchi, Sabato Marco; Reed, Jeremy; Svendsen, Torbjørn; Lee, Chin-Hui. (2009) Exploring Universal Attribute Characterization of Spoken Languages for Spoken Language Recognition. ISCA Interspeech , Brighton 2009-09-06 - 2009-09-10
2008
-
Academic lectureAmdal, Ingunn; Svendsen, Torbjørn; Johnsen, Magne Hallstein; Siniscalchi, Sabato Marco; Hamar, Jarle Bauck; Martinez, Del Hoyo Canterla A.. (2008) SIRKUS - A new paradigm for speech recognition. Norges forskningsråd VERDIKT Conference 2008 , Bergen 2008-10-29 - 2008-10-30
-
Academic lectureAmdal, Ingunn; Strand, Ole Morten; Almberg, Jørn; Svendsen, Torbjørn. (2008) RUNDKAST: An Annotated Norwegian Broadcast News Speech Corpus. European Language Resources Association LREC 2008 , Marrakech 2008-05-26 - 2008-05-31
-
Interview
-
Interview
-
InterviewSvendsen, Torbjørn. (2008) Norsk språkbank. Språkteigen, NRK P2 Språkteigen, NRK P2 [Radio] 2008-08-24
-
Academic lectureSiniscalchi, Sabato Marco; Svendsen, Torbjørn; lee, chin-hui. (2008) A Penalized Logistic Regression Approach to Detection Based Phone Classification. ISCA Interspeech 2008 , Brisbane 2008-09-22 - 2008-09-26
-
Academic lectureSkogstad, Trond; Svendsen, Torbjørn. (2008) Time-Varying Cepstral Coefficients. ISCA ISCA ITRW on Speech Analysis and Processing for Knowledge Discovery , Aalborg 2008-06-04 - 2008-06-06
-
Academic lectureSiniscalchi, Sabato Marco; Svendsen, Torbjørn; lee, chin-hui. (2008) Toward a Detector-Based Universal Phone Recognizer. IEEE International Conference on Acoustics, Speech and Signal Processing , Las Vegas 2008-03-30 - 2008-04-04
-
Academic lectureSiniscalchi, Sabato Marco; Birkenes, Øystein; Johnsen, Magne Hallstein; Svendsen, Torbjørn. (2008) Joint Optimization of Event Detectors and Evidence Merger for Continuous Speech Recognition. ISCA ISCA ITRW on Speech Analysis and Processing for Knowledge Discovery , Aalborg 2008-06-04 - 2008-06-06
2007
-
Academic lectureSiniscalchi, Sabato Marco; Svendsen, Torbjørn; Lee, Chin-Hui. (2007) Towards Bottom-Up Continuous Phone Recognition. IEEE 2007 IEEE Workshop on Automatic Speech Recognition and Understanding , Kyoto 2007-12-09 - 2007-12-13
-
Academic lectureSvendsen, Torbjørn. (2007) Articulatory Features and Segmental Information for Automatic Speech Recognition. European Science Foundation ESF Exploratory Workshop on Models of Language Evolution, Acquisition and Processing , Leuven 2007-11-25 - 2008-11-28
-
InterviewSvendsen, Torbjørn; Abelsen, Atle. (2007) IKE i hver puslebit. Bladet Forskning Bladet Forskning [Newspaper] 2007-12-01
2006
-
Academic lectureAmdal, Ingunn; Johnsen, Magne Hallstein; Svendsen, Torbjørn. (2006) Log Likelihood Ratio Based Annotation Verification of a Norwegian Speech Synthesis Database. NORSIG NORSIG 2006 , Reykjavik 2006-06-07 - 2006-06-09
-
Academic lectureNordgård, Torbjørn; Svendsen, Torbjørn. (2006) Et norsk uttaleleksikon møter en spontan virkelighet. Universitetet i Oslo Oslomålet - et seminar med forskning fra NoTa-korpuset , Oslo 2006-11-23 - 2006-11-24
-
Academic lectureSvendsen, Torbjørn. (2006) Task and speaker adaptation. IEEE og ISCA WISSAP'06 2006-01-04 - 2006-01-07
-
PosterAmdal, Ingunn; Svendsen, Torbjørn. (2006) FonDat1: A Speech Synthesis Corpus for Norwegian. European Language Resources Association LREC 2006 , Genova 2006-05-22 - 2006-05-28
2005
-
Academic lectureSvendsen, Torbjørn; Egeberg, Andreas; Holter, Trym. (2005) VOCALS - Voice centric user interfaces for location based services. NORSIG NORSIG 05 , Stavanger 2005-09-22 - 2005-09-24
-
Academic lectureSvendsen, Torbjørn; Amdal, Ingunn; Bjørkan, Ingmund; Meen, Dyre; Heggtveit, Per Olav; Natvig, Jon Emil. (2005) FONEMA - Tools for realistic speech synthesis in Norwegian. NORSIG NORSIG 05 , Stavanger 2005-09-22 - 2005-09-24
-
PosterMeen, Dyre; Svendsen, Torbjørn; Natvig, Jon-Emil. (2005) Improving Phone Label Aligment Accuracy by Utilizing Voicing Information. University of Patras, Wire Communications Laboratory SPECOM 2005 , Patras 2005-10-17 - 2005-10-19
-
PosterSkogstad, Trond; Svendsen, Torbjørn. (2005) Distributed ASR Using Speech Coder Data for Efficient Feature Vector Representation. ISCA Eurospeech 2005 , Lisboa 2005-09-04 - 2005-09-08
-
PosterBjørkan, Ingmund; Svendsen, Torbjørn; Farner, Snorre. (2005) Comparing Spectral Distance Measures for Join Cost Optimization in Concatenative Speech Synthesis. ISCA Interspeech 2005 , Lisboa 2005-09-04 - 2005-09-08
-
PosterAmdal, Ingunn; Svendsen, Torbjørn. (2005) Unit Selection Synthesis Database Development Using Utterance Verification. ISCA Interspeech 2005 , Lisboa 2005-09-04 - 2005-09-08
2004
-
Academic lectureSvendsen, Torbjørn. (2004) Pronunciation Modeling for Speech Technology. IEEE Signal Processing Society and Indian Institute of Scien 2004 International Conference on Signal Processing and Communications , Bangalore 2004-12-11 - 2004-12-14
-
Academic lectureØien, Geir Egil; Holte, Nils; Andresen, Steinar; Svendsen, Torbjørn; Hammer, Mikael. (2004) Communication technology towards 2020. IME-fakultetet, NTNU/Teknologirådet INFOSAM-2020 conference , Trondheim 2004-04-19 - 2004-04-20
2003
-
PosterMartin, Terrence; Svendsen, Torbjørn; Sridharan, Sridha. (2003) Cross-Lingual Pronunciation Modelling for Indonesian Speech Recognition. Eurospeech 2003 , Geneve 2003-09-04 -
-
PosterWong, Eddie; Martin, Terrence; Svendsen, Torbjørn; Sridharan, Sridha. (2003) Multilingual Phone Clustering for Recognition of Spontaneous Indonesian Speech Utilising Pronunciation Modelling Techniques. Eurospeech 2003 , Geneve 2003-09-04 -
-
Academic lectureSvendsen, Torbjørn. (2003) Pronunciation Modelling for Speech Technology. Queenslad University of Technology , Brisbane, Australia 2003-05-30 -
-
Popular scientific lectureSvendsen, Torbjørn. (2003) Snakke dialekt med mobilen? Om dialektbruk i ny språkteknologi. Noregs mållag , Oslo 2003-09-28 -
-
Popular scientific lectureSvendsen, Torbjørn. (2003) FONEMA - Metodeutvikling for naturtro norsk talesyntese. KUNSTI-seminar 2003 , Bergen 2003-11-18 -
-
Popular scientific lectureSvendsen, Torbjørn. (2003) Speech Processing Activities at NTNU: An Overview. Nordic Speech Technology Seminar , Stockholm 2003-11-14 -
2002
-
Academic lectureAmdal, Ingunn; Svendsen, Torbjørn. (2002) Evaluation of pronunciation variants in the ASR lexicon for different speaking styles. Third International Conference on Language Resources and Evaluation , Las Palmas de Gran Canaria, Spain 2002-05-31 -
2001
-
PosterMyrvoll, Tor Andre; Paliwal, Kuldip K.; Svendsen, Torbjørn. (2001) Fast Adaptation using Constrained Affine Transformations with Hierarchical Priors. Eurospeech 2001 , Aalborg, Sept 3-7, 2001
-
Academic lectureJohnsen, Magne Hallstein; Harborg, Erik; Svendsen, Torbjørn; Amble, Tore; Holter, Trym; Myrvoll, Tor Andre. (2001) SPODIS - Spoken Dialog Systems for Telephony. NORSIG-2001, Norwegian Signal Processing Symposium , Trondheim, Norway, October 18-20 2001
2000
-
Popular scientific lectureSvendsen, Torbjørn. (2000) Ordets makt � om taleteknologi som hjelpemiddel for funksjonshemmede. , "Selvstendig liv", Sjølyst, 12. april, 2000
-
Popular scientific lectureSvendsen, Torbjørn. (2000) Taleteknologi- teknologi med potensiale for kvalitetsheving og effektivisering ved håndtering av informasjon i sykehus. , Norges tekniske vitenskapsakademi, Trondheim, 22. februar, 2000
-
Popular scientific lectureSvendsen, Torbjørn; Johnsen, Magne Hallstein. (2000) �Sesam sesam!� - Kan taleteknologi bli en døråpner for funksjonshemmede?. , Rehabiliteringskonferansen, Trondheim, 20. juni, 2000
-
Popular scientific lectureSvendsen, Torbjørn. (2000) Norsk språkbank, et nasjonalt korpus for språkteknologi. , Statssekretærutvalget for IT, Oslo, 12. januar, 2000
-
Academic lectureJohnsen, Magne Hallstein; Holter, Trym; Svendsen, Torbjørn; Harborg, Erik. (2000) Stochastic Modelling of Semantic Content for Use in a Spoken Dialogue System. 6th International Conference on Spoken Language Processing , Beijing, Oct. 16-20, 2000
-
Academic lectureSvendsen, Torbjørn. (2000) Pronunciation modeling for improved recognition of names. , AT&T Labs, Florham Park, New Jersey, 15. september 2000
-
Academic lectureHolter, Trym; Harborg, Erik; Johnsen, Magne Hallstein; Svendsen, Torbjørn. (2000) ASR-Based Subtitiling of Live TV-Programs for the Hearing Impaired. 6th International Conference on Spoken Language Processing , Beijing, Oct. 16-20, 2000
-
Academic lectureJohnsen, Magne Hallstein; Svendsen, Torbjørn; Amble, Tore; Holter, Trym; Harborg, Erik. (2000) TABOR - A Norwegian Spoken Dialogue System for Bus Travel Information. 6th International Conference on Spoken Language Processing , Beijing, Oct. 16-20, 2000
1999
-
PosterHarborg, Erik; Holter, Trym; Johnsen, Magne Hallstein; Svendsen, Torbjørn. (1999) Subtitling of live broadcast TV-programs for the hearing impaired. AAATE'99 , Dusseldorf, November 1999
-
Popular scientific lectureYang, Qian; Cremelie, Nick; Holter, Trym; Martens, Jean-Pierre; Svendsen, Torbjørn; Ringland, Simon. (1999) Lexicon building and word accuracy in continuous speech recognition. COST 249 meeting, Prague , Prague, Czech Republic, February 1999
-
Academic lectureHarborg, Erik; Holter, Trym; Johnsen, Magne Hallstein; Svendsen, Torbjørn. (1999) Generation of closed captions for live TV-programs using speech recognition. Norsig'99 , Asker, September 1999
-
Academic lectureHarborg, Erik; Holter, Trym; Johnsen, Magne Hallstein; Svendsen, Torbjørn. (1999) On-line captioning of TV-programs for the hearing impaired. EuroSpeech'99 , Budapest, Ungarn
-
Academic lectureJohnsen, Magne Hallstein; Svendsen, Torbjørn. (1999) Menneske/maskin-kommunikasjon basert på tale. MONS-8 (8nde Møte Om Norsk Språk) , Tromsø, Norway, Nov. 1999
-
Academic lectureAmdal, Ingunn; Holter, Trym; Svendsen, Torbjørn. (1999) Modellering av uttalevariasjon for automatisk talegjenkjenning. Møte om norsk språk (MONS 8) , Tromsø, 18.-20. november 1999
-
Academic lectureAmdal, Ingunn; Holter, Trym; Svendsen, Torbjørn. (1999) Maximum likelihood pronunciation modelling of Norwegian natural numbers for automatic speech recognition. NORSIG'99 , Asker, september 1999
1998
-
Popular scientific lecture
-
Popular scientific lectureSvendsen, Torbjørn. (1998) Taleteknologi ved NTNU. Aalborg workshop in speech communication , Aalborg
-
Popular scientific lecture
-
Academic lectureSvendsen, Torbjørn. (1998) SPODIS - Spoken dialog systems for telephony services. Studiemøtet i elektronikk og data , Kristiansand
-
Academic lectureHolter, Trym; Svendsen, Torbjørn. (1998) Maximum likelihood modelling of pronunciation variation. ESCA Tutorial and Research Workshop on Modeling Pronunciation Variation for ASR , Rolduc
1997
-
Popular scientific lectureHolter, Trym; Svendsen, Torbjørn. (1997) Combined optimisation of baseforms and model parameters in speech recognition based on acoustic sub-word units. , AT&T Labs, Florham Park, NJ, USA
-
Popular scientific lectureSvendsen, Torbjørn. (1997) Some topics from recent work in speech processing. , Motorola Research Labs, Sydney og University of Wollongong
-
Popular scientific lectureSvendsen, Torbjørn. (1997) Speech recognition based on acoustic subword units. , Telenor FoU, Kjeller
-
Popular scientific lectureSvendsen, Torbjørn. (1997) Acoustic subwords - some applications in speech processing. , Griffith University, Brisbane, Australia
-
Academic lectureHolter, Trym; Svendsen, Torbjørn. (1997) A joint segmentation and labelling scheme for use in acoustic subword based speech recognition. Norwegian Signal Processing Symposium , Tromsø
-
Academic lectureHolter, Trym; Svendsen, Torbjørn. (1997) Combined optimisation of baseforms and model parameters in speech recognition based on acoustic subword units. IEEE Speech recognition Workshop , Santa Barbara, Calif.
-
Academic lectureHolter, Trym; Svendsen, Torbjørn. (1997) Incorporating linguistic knowledge and automatic baseform generation in acoustic subword unit based speech recognition. Eurospeech '97 , Rhodos
1996
-
Academic lecturePihl, Johnny; Johnsen, Magne Hallstein; Svendsen, Torbjørn. (1996) A VLSI implementation of pdf computations in HMM based speech recognition. IEEE TENCON-96 , Perth 1996-11-27 - 1996-11-29
1995
-
Academic lectureJohnsen, Magne Hallstein; Svendsen, Torbjørn; Harborg, Erik. (1995) Experiments on cepstral mean subtraction and Rasta-filtering applied to SAMPA phoneme recognition. COST COST249 , Nancy 1995-05-06 - 1995-05-07
1994
-
Academic lectureSvendsen, Torbjørn. (1994) Segmental quantization of speech spectral information. IEEE International Conference on Acoustics, Speech and Signal Processing , [Mangler data]
-
Popular scientific lectureSvendsen, Torbjørn. (1994) Acoustic segmentation of speech : applications in speech processing. , [Mangler data]
-
Popular scientific lectureSvendsen, Torbjørn. (1994) Acoustic segmentation of speech : applications in speech processing. , [Mangler data]
1993
-
Academic lectureSvendsen, Torbjørn. (1993) Efficient quantization of speech spectral information. EUROSPEECH '93 (1993 : Berlin) , [Mangler data]
1989
-
Academic lectureSvendsen, Torbjørn Karl; Paliwal, Kuldip K.; Harborg, Erik; Husøy, Per Ove. (1989) An Improved Sub-Word Based Speech Recognizer. International Conference on Acoustics, Speech, and Signal Processing (ICASSP) , Glasgow 1989-05-01 -
1988
-
Academic lectureSvendsen, Torbjørn Karl; Paliwal, K.K.; Harborg, Erik; Husøy, P.O.. (1988) Experiments with a Sub-Word Based Speech Recognizer. International Conference on Speech Science and Technology (ICSST) , Sydney 1988-12-01 -