WIPO logo
Mobile | Deutsch | Español | Français | 日本語 | 한국어 | Português | Русский | 中文 | العربية |
PATENTSCOPE

Search International and National Patent Collections
World Intellectual Property Organization
Search
 
Browse
 
Translate
 
Options
 
News
 
Login
 
Help
 
Machine translation
1. (WO2002029612) METHOD AND SYSTEM FOR GENERATING AND SEARCHING AN OPTIMAL MAXIMUM LIKELIHOOD DECISION TREE FOR HIDDEN MARKOV MODEL (HMM) BASED SPEECH RECOGNITION
Latest bibliographic data on file with the International Bureau   

Pub. No.:    WO/2002/029612    International Application No.:    PCT/CN2000/000296
Publication Date: 11.04.2002 International Filing Date: 30.09.2000
IPC:
G10L 15/14 (2006.01)
Applicants: INTEL CORPORATION [US/US]; 2200 Mission College Boulevard, Santa Clara, CA 95052 (US) (For All Designated States Except US).
GUO, Qing [CN/CN]; (CN) (For US Only).
YAN, Yonghong [CN/CN]; (CN) (For US Only).
YUAN, Baosheng [SG/SG]; (SG) (For US Only).
ZHAO, Quingwei [CN/CN]; (CN) (For US Only).
LIN, Zhiwei [SG/SG]; (SG) (For US Only)
Inventors: GUO, Qing; (CN).
YAN, Yonghong; (CN).
YUAN, Baosheng; (SG).
ZHAO, Quingwei; (CN).
LIN, Zhiwei; (SG)
Agent: CCPIT PATENT AND TRADEMARK LAW OFFICE; 8th Floor, 2 Fuchengmenwai St., Beijing 100037 (CN)
Priority Data:
Title (EN) METHOD AND SYSTEM FOR GENERATING AND SEARCHING AN OPTIMAL MAXIMUM LIKELIHOOD DECISION TREE FOR HIDDEN MARKOV MODEL (HMM) BASED SPEECH RECOGNITION
(FR) PROCEDE ET SYSTEME DE GENERATION ET DE RECHERCHE D'UN ARBRE DE DECISION CONCERNANT LA PROBABILITE MAXIMALE OPTIMALE DANS LE CADRE DE LA RECONNAISSANCE VOCALE UTILISANT LE MODELE DE MARKOV CACHE (HMM)
Abstract: front page image
(EN)A method and system for generating and searching an optimal likelihood decision tree for hidden markov model (HMM) based speech recognition are described. Speech signals are received. The received speech signals are processed to generate a plurality of phoneme clusters. The phoneme clusters are grouped into a first cluster node and a second cluster node. A determination is made if a phoneme cluster in the first cluster note is to be moved into the second cluster node based on a likelihood increase of the phone cluster of the first cluster node from being in the first cluster node to being in the second cluster node.
(FR)L'invention concerne un procédé et un système de génération et de recherche d'un arbre de décision concernant la probabilité maximale optimale dans le cadre de la reconnaissance vocale utilisant le modèle de Markov caché (HMM). Après réception des signaux vocaux, le procédé les traite afin de générer une pluralité de groupes de phonèmes qui sont réunis en un premier noeud de groupe et en un second noeud de groupe. Si un groupe de phonèmes présent dans le premier noeud doit être déplacé dans le second noeud, car il existe une plus grande probabilité que le groupe de phonèmes concerné rattaché au premier noeud se trouve dans le second noeud, une détermination a lieu.
Designated States: AE, AG, AL, AM, AT, AU, AZ, BA, BB, BG, BR, BY, BZ, CA, CH, CN, CR, CU, CZ, DE, DK, DM, DZ, EE, ES, FI, GB, GD, GE, GH, GM, HR, HU, ID, IL, IN, IS, JP, KE, KG, KP, KR, KZ, LC, LK, LR, LS, LT, LU, LV, MA, MD, MG, MK, MN, MW, MX, MZ, NO, NZ, PL, PT, RO, RU, SD, SE, SG, SI, SK, SL, TJ, TM, TR, TT, TZ, UA, UG, US, UZ, VN, YU, ZA, ZW.
African Regional Intellectual Property Organization (GH, GM, KE, LS, MW, MZ, SD, SL, SZ, TZ, UG, ZW)
Eurasian Patent Organization (AM, AZ, BY, KG, KZ, MD, RU, TJ, TM)
European Patent Office (AT, BE, CH, CY, DE, DK, ES, FI, FR, GB, GR, IE, IT, LU, MC, NL, PT, SE)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GW, ML, MR, NE, SN, TD, TG).
Publication Language: English (EN)
Filing Language: English (EN)