Dynamic programming search for continuous speech recognition

被引：90

作者：

Ney, H ^{[1
]}

Ortmanns, S

机构：

[1] Rhein Westfal TH Aachen, Dept Comp Sci, Aachen, Germany

[2] Lucent Technol, Bell Labs, Dialogue Res Dept, Murray Hill, NJ USA

来源：

IEEE SIGNAL PROCESSING MAGAZINE | 1999年 / 16卷 / 05期

关键词：

D O I：

10.1109/79.790984

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Search strategies based on dynamic programming (DP) are used for a large number of speech recognition tasks, ranging from digit string recognition through medium-size vocabulary recognition using heavily constrained grammars to large-vocabulary continuous speech recognition (LVCSR) with virtually unconstrained speech input. A unifying view of the DP approach to the LVCSR problem is presented.

引用

页码：64 / 83

页数：20

共 80 条

[1]

ALLEVA F, 1996, P IEEE INT C AC SPEE, P133

[2]

ALLEVA F, 1993, P IEEE INT C AC SPEE, V2, P307

[3]

[Anonymous], 2010, Dynamic programming

[4]

[Anonymous], P IEEE INT C AC SPEE

[5]

ANTONIOL G, 1995, P IEEE INT C AC SPEE, V1, P588

[6]

AUBERT X, 1995, P IEEE INT C AC SPEE, P49

[7]

Austin S., 1991, P IEEE INT C AC SPEE, P697

[8] DECODING FOR CHANNELS WITH INSERTIONS, DELETIONS, AND SUBSTITUTIONS WITH APPLICATIONS TO SPEECH RECOGNITION [J].

BAHL, LR ;

JELINEK, F .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1975, 21 (04) :404-411

[9] A MAXIMUM-LIKELIHOOD APPROACH TO CONTINUOUS SPEECH RECOGNITION [J].

BAHL, LR ;

JELINEK, F ;

MERCER, RL .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1983, 5 (02) :179-190

[10]

Baker J.K., 1975, Speech recognition, P512

← 1 2 3 4 5 6 7 8 →