Processing

Please wait...

Settings

Settings

1. EP2389672 - METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR PROVIDING COMPOUND MODELS FOR SPEECH RECOGNITION ADAPTATION

Office European Patent Office
Application Number 10733288
Application Date 21.01.2010
Publication Number 2389672
Publication Date 30.11.2011
Publication Kind B1
IPC
G PHYSICS
10
MUSICAL INSTRUMENTS; ACOUSTICS
L
SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15
Speech recognition
06
Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
G PHYSICS
10
MUSICAL INSTRUMENTS; ACOUSTICS
L
SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15
Speech recognition
06
Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
065
Adaptation
07
to the speaker
G PHYSICS
10
MUSICAL INSTRUMENTS; ACOUSTICS
L
SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
17
Speaker identification or verification
20
Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions
G10L 15/06
G10L 15/07
G10L 17/20
CPC
G10L 17/20
G10L 15/07
Applicants NOKIA TECHNOLOGIES OY
Inventors OLSEN JESPER
Designated States
Priority Data 2010000106 21.01.2010 IB
12356814 21.01.2009 US
Title
(DE) VERFAHREN, VORRICHTUNG UND COMPUTERPROGRAMMPRODUKT ZUR BEREITSTELLUNG VON VERBUNDMODELLEN ZUR SPRACHERKENNUNGSADAPTION
(EN) METHOD, APPARATUS AND COMPUTER PROGRAM PRODUCT FOR PROVIDING COMPOUND MODELS FOR SPEECH RECOGNITION ADAPTATION
(FR) PROCÉDÉ, APPAREIL ET PRODUIT PROGRAMME D'ORDINATEUR POUR FOURNIR DES MODÈLES COMPOSÉS POUR UNE ADAPTATION DE RECONNAISSANCE VOCALE
Abstract
(EN)
An apparatus for providing compound models for speech recognition adaptation includes a processor. The processor may be configured to receive a speech signal corresponding to a particular speaker, select a cluster model including both a speaker independent portion and a speaker dependent portion based at least in part on a characteristic of speech of the particular speaker, and process the speech signal using the selected cluster model. A corresponding method and computer program product are also provided.

(FR)
L'invention porte sur un appareil pour fournir des modèles composés pour une adaptation de reconnaissance vocale, lequel appareil comprend un processeur. Le processeur peut être configuré pour recevoir un signal vocal correspondant à un locuteur particulier, sélectionner un modèle de groupe comprenant à la fois une partie indépendante du locuteur et une partie dépendante du locuteur sur la base au moins en partie d'une caractéristique vocale du locuteur particulier; et traiter le signal vocal à l'aide du modèle de groupe sélectionné. L'invention porte également sur un procédé et un produit programme d'ordinateur correspondants.