EP 1490862 A1 20041229 - SPEECH RECOGNITION METHOD
Title (en)
SPEECH RECOGNITION METHOD
Title (de)
VERFAHREN ZUR SPRACHERKENNUNG
Title (fr)
PROCEDE DE RECONNAISSANCE DE LA PAROLE
Publication
Application
Priority
- FR 0300653 W 20030319
- FR 0204285 A 20020329
Abstract (en)
[origin: WO03083830A1] The invention relates to a method of translating input data AVin into at least one output sequence (OUTSQ). The inventive method comprises a decoding step during which sub-lexical entities having representative input data (AVin) are identified using a first model (MD 11) and during which different possible combinations of the aforementioned sub-lexical entities are generated as said sub-lexical entities are identified and with reference to a second model (MD3). The invention also involves the storing of several possible combinations [nj;hq;Sq] of the above-mentioned sub-lexical entities, the most likely combination being intended to form the output lexical sequence (OUTSQ) and one such storage operation enabling the structure of the second model (MD3) to be simplified.
IPC 1-7
IPC 8 full level
G10L 15/14 (2006.01); G10L 15/183 (2013.01); G10L 15/02 (2006.01)
CPC (source: EP US)
G10L 15/142 (2013.01 - EP US); G10L 15/183 (2013.01 - EP US); G10L 2015/025 (2013.01 - EP US)
Citation (search report)
See references of WO 03083830A1
Designated contracting state (EPC)
AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LI LU MC NL PT RO SE SI SK TR
DOCDB simple family (publication)
WO 03083830 A1 20031009; AU 2003229846 A1 20031013; EP 1490862 A1 20041229; FR 2837969 A1 20031003; US 2005154581 A1 20050714
DOCDB simple family (application)
FR 0300653 W 20030319; AU 2003229846 A 20030319; EP 03722681 A 20030319; FR 0204285 A 20020329; US 50965105 A 20050316