Svendsen, Torbj�rn - Department of Electronics and Telecommunications, Norwegian University of Science and Technology

Advanced Search

Svendsen, Torbj�rn - Department of Electronics and Telecommunications, Norwegian University of Science and Technology

On the Automatic Segmentation of Speech Signals TorbjBm Svendsent
A Joint Segmentation and Labelling Scheme for use in Acoustic Subword Based Speech Recognition
STOCHASTIC MODELING OF SEMANTIC CONTENT FOR USE IN A SPOKEN DIALOGUE SYSTEM
TorbjGrn Svendsen N-7034 Trondheim-NTH
TOWARD A DETECTOR-BASED UNIVERSAL PHONE RECOGNIZER Sabato Marco Siniscalchi1
TABOR -A NORWEGIAN SPOKEN DIALOGUE SYSTEM FOR BUS TRAVEL INFORMATION
JOINT OPTIMIZATION OF EVENT DETECTORS AND EVIDENCE MERGER FOR CONTINUOUS PHONE RECOGNITION
Articulatory Features and Segmental Information for Automatic Speech Recognition
TOWARDS BOTTOM-UP CONTINUOUS PHONE RECOGNITION Sabato Marco Siniscalchi1
$65%$6(' 68%7,7/,1* 2) /,9( 79352*5$06 )25 7+( +($5,1* ,03$,5('
MAXIMUM LIKELIHOOD MODELLING OF PRONUNCIATION VARIATION Trym Holter1 and Torbj rn Svendsen2
Combined Optimisation of Baseforms and Model Parameters in Speech Recognition Based on Acoustic
A Comparison of Lexicon-Building Methods for Subword-Based Speech Recognisers
COMBINED OPTIMISATION OF BASEFORMS AND SUBWORD MODELS FOR AN HMM BASED SPEECH RECOGNISER
In speech coding quantization has tra-ditionally been done on a sample by
PRONUNCIATION MODELING FOR SPEECH TECHNOLOGY Torbjrn Svendsen
Improving Phone Label Alignment Accuracy by Utilizing Voicing Information Dyre Meen, Torbjrn Svendsen
SEGMENTAL QUANTIZATION OF SPEECH SPECTRAL INFORMATION Torbjem Svenuken
Evaluation of Pronunciation Variants in the ASR Lexicon for Different Speaking Styles
VOCALS VOICE CENTRIC USER INTERFACES FOR LOCATION BASED Torbjrn Svendsen, 1
FONEMA TOOLS FOR REALISTIC SPEECH SYNTHESIS IN NORWEGIAN Torbjrn Svendsen1
Time-Varying Cepstral Coefficients Trond Skogstad, Torbjrn Svendsen
A TIME-FREQUENCY SEGMENTAL NEURAL NETWORK FOR PHONEME RECOGNITION