Torbjørn Svendsen

Publications

Home

Biography

Publications

Projects

Other Activities

Links



2010
Experimental Studies on Continuous Speech Recognition Using Neural Architectures with ‘Adaptive’ Hidden Activation Functions
Proc. ICASSP 2010, Dallas, Texas, March 2010
S.M.Siniscalchi, T.Svendsen, F.Sorbello, C.-H.Lee
Spontal-N: A Corpus of Interactional Spoken Norwegian
Proc. LREC-2010, Valetta, Malta, May 2010
R.O.Sikveland, A.Öttl, I.Amdal, M.Ernestus, T.Svendsen, J.Edlund
NameDat: A Database of English Proper Names Spoken by Native Norwegian
Proc. LREC-2010, Valetta, Malta, May 2010
L.Adde, T.Svendsen
A Minimum Classification Error Approach to Pronunciation Variation Modeling of Non-Native Proper Names
Proc. Interspeech 2010; Makuhari, Japan, Sept 2010
L.Adde, B.Reveil, J.-P.Martens, T.Svendsen
The NTNU Concatenative Speech Synthesizer
Proc. Blizzard Challenge Workshop 2010; Kyoto, Japan, Sept 2010
D.Meen, T.Svendsen
Exploiting Context-Dependency and Acoustic Resolution of Universal Speech Attribute Models in Spoken Language Recognition
Proc. Interspeech 2010; Makuhari, Japan, Sept 2010
S.M.Siniscalchi, J.Reed, T.Svendsen, C.-H.Lee
Intra-Frame Variability As a Predictor of Frame Classifiability
Proc. Interspeech 2010; Makuhari, Japan, Sept 2010
T.Skogstad, T.Svendsen
UEF-NTNU System Description for Albayzin 2010 Language Recognition Evaluation
Proc. FALA 2010; Vigo, Spain, Nov 2010
R. Saeidi, M. Soufifar, T. Kinnunen, T. Svendsen, P. Fränti
A Survey on Recent Progress in the ASAT/SIRKUS Paradigm (invited paper)
Proc. ISCSLP 2010; Tainan, Taiwan, Dec 2010
S.M.Siniscalchi, T.Svendsen, C.H.Lee
A Comparative Analysis of Discriminative and Non-Discriminative Pronunciation Priors in Pronunciation Variation Modeling
Proc. IEEE Workshop on Spoken Language Technology 2010; San Francisco, USA, Dec 2010
L.Adde, T.Svendsen
2009
A Phonetic Feature Based Lattice Rescoring Approach to LVCSR
Proc. ICASSP 2009, Taipei, Taiwan, April 2009
S.M.Siniscalchi, T.Svendsen, C.-H.Lee
Exploring Universal Attribute Characterization of Spoken Languages for Spoken Language Recognition
Proc. Interspeech 2009, Brighton, Sept. 2009
S.M.Siniscalchi, J.Reed, T.Svendsen, C.-H.Lee
Lexicon Adaptation for Subword Speech Recognition
Proc. ASRU 2009, Merano, Italy, Dec. 2009
T.Mertens, D.Schneider, A.B.Næss, T.Svendsen
2008
A Penalized Logistic Regression Approach to Detection Based Phone Classification
Proc. Interspeech 2008, Brisbane, Australia, Sept. 2008
S.M.Siniscalchi, T.Svendsen, C.-H.Lee
Joint Optimization of Event Detectors and Evidence Merger for Continuous Speech Recognition
ISCA ITRW on Speech Analyis and Processing for Knowledge Discovery, Aalborg, Denmark, June 2008
S.M.Siniscalchi, Ø.Birkenes, M.H.Johnsen, T.Svendsen
Time-Varying Cepstral Coefficients
ISCA ITRW on Speech Analyis and Processing for Knowledge Discovery, Aalborg, Denmark, June 2008
T.Skogstad, T.Svendsen
RUNDKAST: An Annotated Norwegian Broadcast News Corpus
LREC 2008, Marrakech, Morocco, May 2008
I.Amdal, O.M.Strand, J.Almberg, T.Svendsen
Toward A Detector-Based Universal Phone Recognizer
ICASSP 2008, Las Vegas, Nevada, April 2008
S.M.Siniscalchi, T.Svendsen, C.-H.Lee
2007
Articulatory Features And Segmental Information for Automatic Speech Recognition
ESF Exploratory Workshop on Models of Language Evolution, Acquisition and Processing, Leuven, Belgium, Nov. 2007
T.Svendsen
Towards Bottom-Up Phone Recognition
Proc. ASRU 2007, Kyoto, Japan, Dec. 2007
S.M.Siniscalchi, T.Svendsen, C.-H.Lee
2006
Log Likelihood Ratio Based Annotation Verification of a Norwegian Speech Synthesis Database
Proc. Norsig-2006, Reykjavik, Iceland, June 2006
I.Amdal, M.H.Johnsen, T.Svendsen
FonDat1 - A Speech Synthesis Corpus for Norwegian
Proc. LREC-2006, Genoa, Italy, June 2006
I.Amdal, T.Svendsen
2005
Improving Phone Label Alignment by Utilizing Voicing Information
Proc. SPECOM-2005, Patras, Greece, Oct. 2005
D.Meen, T.Svendsen
VOCALS - Voice Centric User Interfaces for Location Based Services
Proc. NORSIG-2005, Stavanger, Sept. 2005
T.Svendsen, A.Egeberg, T.Holter, T.Skogstad
FONEMA - Tools for Realistic Speech Synthesis in Norwegian
Proc. NORSIG-2005, Stavanger, Sept. 2005
T.Svendsen, I.Amdal, I,Bjørkan, P.O.Heggtveit, J.E.Natvig
Distributed ASR Using Speech Coder Data for Efficient Feature Vector Representation
Proc. Eurospeech 2005, Lisbon, Sept. 2005
T.Skogstad, T.Svendsen

Unit Selection Synthesis Database Development Using Utterance Verification
Proc. Eurospeech 2005, Lisbon, Sept. 2005
I.Amdal, T.Svendsen
Comparing Spectral Distance Measures for Join Cost Optimization in Concatenative Speech Synthesis
Proc. Eurospeech 2005, Lisbon, Sept. 2005
I.Bjørkan
, T.Svendsen, S.Farner
 
 
2004
 
Pronunciation Modeling for Speech Technology
Proc. 2004 International Conference on Signal Processing and Communications; Bangalore, 2004
 T.Svendsen
 

2003


Speech Technology: Past, Present and Future

Telektronikk, vol 99, no. 2, pp. 6-18, 2003
            T.Svendsen

Cross-Lingual Pronunciation Modelling for Indonesian Speech Recognition
Proc. Eurospeech 2003, Geneva, Sept. 2003
 T.Martin, T.Svendsen, S.Sridharan

Multilingual Phone Clustering for Recognition of Spontaneous Indonesian Speech Utilising Pronunciation Modelling Techniques
Proc. Eurospeech 2003, Geneva, Sept. 2003
E.Wong, T.Martin, T.Svendsen, S.Sridharan
 

2002
 
Evaluation of Pronunciation Variants in the ASR Lexicon for Different Speaking Styles
Proc. LREC-2002, Las Palmas, May 2002
I.Amdal, T.Svendsen

Roles for Speech Technology in the Information Society
in E. Panzar (ed.): Perspectives on the Age of the Information Society, Reports of the Information Research Programme of the Academy of Finland, pp. 229-238, Tampere 2002
T.Svendsen

 
2001
 
SPODIS – Spoken Dialog Systems for Telephony
Proc. Norsig 2001, Trondheim, October 2001
M.H.Johnsen, E.Harborg, T.Svendsen, T.Amble, T.Holter, T.A.Myrvoll, T.Nordgård

Nordisk forskningssamarbeid innen språkteknologi (Nordic research cooperation in language technology, in Norwegian)
Språknytt, vol 3/2001, pp. 24-28, Sept. 2001
T.Svendsen

Fast Adaptation using Constrained Affine Transformations with Hierarchical Priors
Proc. Eurospeech 2001, Aalborg, Sept. 2001
T.A.Myrvoll, K.K.Paliwal, T.Svendsen

2000
Modellering av uttalevariasjon for automatisk talegjenkjenning (Modelling pronunciation variation for automatic speech recognition, in Norwegian)
Nordlyd, vol. 28-2000, pp. 74-87, 2000
I.Amdal, T.Holter, T.Svendsen

TABOR - A Norwegian Spoken Dialogue System for Bus Travel Information
Proc. ICSLP’2000, Beijing, Oct. 2000
M.H.Johnsen, T.Svendsen, T.Amble, T.Holter, E.Harborg
 
ASR-Based Subtitiling of Live TV-Programs for the Hearing Impaired
Proc. ICSLP’2000, Beijing, Oct. 2000
T.Holter, E.Harborg, M.H.Johnsen, T.Svendsen

Stochastic Modelling of Semantic Content for Use in a Spoken Dialogue System
Proc. ICSLP’2000, Beijing, Oct. 2000
M.H.Johnsen, T.Holter, T.Svendsen, E.Harborg
Pre 2000
Maximum likelihood modelling of pronunciation variation
Speech Communications, Nov. 1999
T.Holter, T.Svendsen

On-line captioning of TV-programs for the hearing impaired
Proc. Eurospeech'99, Budapest, Sept. 1999
E.Harborg, T.Holter, M.H.Johnsen, T.Svendsen
Maximum likelihood modelling of pronunciation variation
ESCA Tutorial and Research Workshop on ``Modeling pronunciation variation for ASR'', Kerkrade, The Netherlands, May 1998
T.Holter, T.Svendsen

Combined Optimisation of Baseforms and Model Parameters in Speech Recognition Based on Acoustic Subword Units
Proc. IEEE Workshop on Automatic Speech Recognition, Santa Barbara, Dec. 1997
T.Holter, T.Svendsen

Incorporating Linguistic Knowledge and Automatic Baseform Generation in Acoustic Subword Unit Based Speech Recognition
Proc. Eurospeech'97, Rhodos, Sept. 1997
T.Holter, T.Svendsen

A Joint Segmentation and Labelling Scheme for Use in Acoustic Subword Based Speech Recognition
Proc. Norsig'97, Tromsø, May 1997
T.Holter, T.Svendsen

A Comparison of Lexicon-Building Methods for Subword-Based Speech Recognition
Proc. IEEE Tencon, Perth, Nov. 1996
T.Holter, T.Svendsen

Combined Optimisation of Baseforms and Subword Models for an HMM Based Speech Recogniser
Proc. ISSPA'96, Gold Coast, Nov. 1996
T.Holter, T.Svendsen

Training of Lexica for Subword-Based Speech Recognisers
Proc. NORSIG-95, Stavanger, Sept. 1995
T.Holter, T.Svendsen

Optimal acoustic baseforms for HMM-based speech recognition
Proc. Eurospeech'95, Madrid, Sept. 1995
T.Svendsen, F.K.Soong, H.Purnhagen

Access Control Using Speaker Verification
Proc. NORSIG-94, pp. 130-133, Ålesund, June, 1994
T.Svendsen, B.T.Jensen

Segmental Quantization of Speech Spectral Information
Proc. ICASSP'94, pp. , Adelaide, April, 1994
T. Svendsen

COST232: Speech Recognition Over the Telephone Line
Proc. EUROSPEECH'93, pp. 1845-1848, Berlin, Sept. 1993
A.Paoloni, T.Svendsen, B.Kaspar, D.Johnston, G.Hult

Efficient Quantization of Speech Spectral Information
Proc. EUROSPEECH'93, pp. 1143-1146, Berlin, Sept. 1993
T.Svendsen

A Time-Frequency Segmental Neural Network for Phoneme Recogniton
Proc. ICASSP'93, pp. I509-I512, Minneapolis, April 1993
A.Basu, T.Svendsen

The self-excited, stochastic multipulse coder
Journal of Electrical and Electronics Engineering, Australia, pp. 183-187, September 1991
B.Ribbum, A.Perkis, T.Svendsen

ANN-based speech recognition using a preprocessor for non-linear time compression
Proc. Eurospeech'91, Genova, Italy, 1991.
P.O. Husøy, T. Svendsen

Automatic alignment of phonemic labels with continuous speech
Proc. ICSLP'90, Kobe, Japan, 1990.
T. Svendsen, K. Kvale

Speech Processing Activities in the Nordic Countries
Proc. Speech Tech'90, New York, 1990.
T. Svendsen

An Improved Sub-Word Based Speech Recognizer
Proc. ICASSP'89, Glasgow, 1989
T. Svendsen, K. K. Paliwal, E. Harborg, P. O. Husøy

Experiments with a Sub-Word Based Speech Recognizer
2nd Australian Conf. on Speech Science and Technology, Sydney, Australia, 1988.
T. Svendsen, K. K. Paliwal, E. Harborg, P. O. Husøy

Speech Recognition- An Overview
Telecommunications, Vol. 21, No. 12, Dec. 1987.
T. Svendsen

On the Automatic Segmentation of Speech Signals
Proc. ICASSP'87, Dallas, 1987.
T. Svendsen, F. K. Soong

Multi-Dimensional Quantization Applied to Predictive Coding of Speech
Proc. ICASSP'86, Tokyo.
T.Svendsen

A Speaker Independent Isolated Word Recognizer for a Norwegian Vocabulary
Proc. Nordic Conf. on Speech Processing, Trondheim, March 1986
M.H. Johnsen, T.Svendsen

Speech processing in Norway
Proc. Nordic Conf. on Speech Processing, Trondheim, March 1986.
T.Svendsen

Multi-Dimensional Quantization Applied to Predictive Coding of Speech
Ph.D thesis, The Norwegian Institute of Technology, March 1985.
T.Svendsen

A Study of Three Coders (Sub-Band, RELP and MPE) for speech with Additive White Noise
Proc. ICASSP'85.
K.K.Paliwal, T.Svendsen

Comparative Evaluations of LP Analysis Methods for Multi-Pulse Excited LP Coding of Speech
Proc. of The Institute of Acoustics Autumn Conference, Windermere, Great Britain, 1984.
T.Svendsen, K.K.Paliwal

Tree Encoding of the LPC Residual
Proc.ICASSP'84, San Diego
T. Svendsen

Effects of Rayleigh Fading on Medium Bandwidth Speech Coders
Proc.EUSIPCO'83,pp 539-542
T.Svendsen
Miscellaneous publications and technical reports.