Processing

Please wait...

Settings

Settings

1. WO2000043990 - SPEECH RECOGNITION DEVICE INCLUDING A SUB-WORD MEMORY

Publication Number WO/2000/043990
Publication Date 27.07.2000
International Application No. PCT/EP1999/010302
International Filing Date 20.12.1999
IPC
G10L 15/18 2006.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
18using natural language modelling
CPC
G10L 15/187
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
18using natural language modelling
183using context dependencies, e.g. language models
187Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
G10L 15/197
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
15Speech recognition
08Speech classification or search
18using natural language modelling
183using context dependencies, e.g. language models
19Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
197Probabilistic grammars, e.g. word n-grams
Applicants
  • KONINKLIJKE PHILIPS ELECTRONICS N.V. [NL/NL]; Groenewoudseweg 1 NL-5621 BA Eindhoven, NL
Inventors
  • BARTOSIK, Heinrich; NL
  • KLAKOW, Dietrich, G.; NL
Agents
  • RÖGGLA, Harald; Internationaal Octrooibureau B.V. Prof. Holstlaan 6 NL-5656 AA Eindhoven, NL
Priority Data
99890001.305.01.1999EP
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SPEECH RECOGNITION DEVICE INCLUDING A SUB-WORD MEMORY
(FR) DISPOSITIF DE RECONNAISSANCE DE LA PAROLE COMPORTANT UNE MEMOIRE DE SOUS-MOTS
Abstract
(EN)
In a speech recognition device (2) comprising a word memory (10) in which word information (WI) and assigned phoneme information (PI(WI)) of at least a first and a second word forming the vocabulary can be stored, and including a sub-word memory (11) in which sub-words forming parts of words can be stored as sub-word information (SWI) and assigned phoneme information (PI(SWI)) of at least a first and a second sub-word, and speech model word memory (12) is provided in which at least a probability of occurrence of the second word after the first word in a word sequence formed by these words can be stored as transition probability information (UWI(WFI)).
(FR)
L'invention se rapporte à un dispositif de reconnaissance de la parole (2) comportant une mémoire de mots (10) utilisée pour le stockage d'informations relatives à des mots (WI) et d'informations relatives à des phonèmes associés (PI(WI)) d'au moins un premier et un second mot composant le vocabulaire. Ce dispositif comporte également une mémoire de sous-mots (11) dans laquelle des sous-mots formant des parties de mots peuvent être stockés en tant qu'informations relatives à des sous-mots (SWI) et informations relatives aux phonèmes associés (PI(SWI)) d'au moins un premier et un second sous-mot. En outre, une mémoire de mots (12) pour modèles de la parole permet le stockage d'au moins une probabilité d'occurrence du second mot à la suite du premier mot dans une séquence constituée par ces mots, et ce sous forme d'une information de probabilité de transition (UWI(WFI)).
Latest bibliographic data on file with the International Bureau