A STOCHASTIC SEGMENT MODEL FOR PHONEME-BASED CONTINUOUS SPEECH RECOGNITION

被引：79

作者：

OSTENDORF, M ^{[1
]}

ROUKOS, S ^{[1
]}

机构：

[1] IBM CORP,THOMAS J WATSON RES CTR,YORKTOWN HTS,NY 10598

来源：

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING | 1989年 / 37卷 / 12期

关键词：

D O I：

10.1109/29.45533

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

引用

页码：1857 / 1869

页数：13

共 17 条

[1] A MAXIMUM-LIKELIHOOD APPROACH TO CONTINUOUS SPEECH RECOGNITION
BAHL, LR
JELINEK, F
MERCER, RL
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1983, 5 (02) : 179 - 190
[2] BAHL LR, 1981, APR P IEEE INT C AC, P1149
[3] FRAME-SPECIFIC STATISTICAL FEATURES FOR SPEAKER INDEPENDENT SPEECH RECOGNITION
BOCCHIERI, EL
DODDINGTON, GR
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1986, 34 (04): : 755 - 764
[4] ISOLATED-WORD SPEECH RECOGNITION USING MULTISECTION VECTOR QUANTIZATION CODEBOOKS
BURTON, DK
SHORE, JE
BUCK, JT
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1985, 33 (04): : 837 - 849
[5] NETWORK-BASED CONNECTED DIGIT RECOGNITION
BUSH, MA
KOPEC, GE
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1987, 35 (10): : 1401 - 1413
[6] CHOW YL, 1986, APR P IEEE INT C AC, P1593
[7] HELSTROM CW, 1975, STATISTICAL THEORY S
[8] MIXTURE AUTOREGRESSIVE HIDDEN MARKOV-MODELS FOR SPEECH SIGNALS
JUANG, BH
RABINER, LR
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1985, 33 (06): : 1404 - 1413
[9] NETWORK-BASED ISOLATED DIGIT RECOGNITION USING VECTOR QUANTIZATION
KOPEC, GE
BUSH, MA
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1985, 33 (04): : 850 - 867
[10] LEE KF, 1988, APR P IEEE INT C AC