SHORTLIST - A CONNECTIONIST MODEL OF CONTINUOUS SPEECH RECOGNITION

被引：730

作者：

NORRIS, D ^{[1
]}

机构：

[1] MAX PLANCK INST PSYCHOLINGUIST, NIJMEGEN, NETHERLANDS

来源：

COGNITION | 1994年 / 52卷 / 03期

关键词：

D O I：

10.1016/0010-0277(94)90043-4

中图分类号：

B84 [心理学];

学科分类号：

04 ; 0402 ;

摘要：

Previous work has shown how a back-propagation network with recurrent connections can successfully model many aspects of human spoken word recognition (Norris, 1988, 1990, 1992, 1993). However. such networks are unable to revise their decisions in the light of subsequent context. TRACE (McClelland & Elman, 1986), on the other hand, manages to deal appropriately with following context, but only by using a highly implausible architecture that fails to account for some important experimental results. A new model is presented which displays the more desirable properties of each of these models. In contrast to TRACE the new model is entirely bottom-up and can readily perform simulations with vocabularies of tens of thousands of words.

引用

页码：189 / 234

页数：46

共 50 条

[21] A hierarchical Bayesian model for continuous speech recognition
Mouria-beji, F
[J]. PATTERN RECOGNITION LETTERS, 2002, 23 (07) : 773 - 781
[22] Tandem connectionist feature extraction for conversational speech recognition
Zhu, QF
Chen, B
Morgan, N
Stolcke, A
[J]. MACHINE LEARNING FOR MULTIMODAL INTERACTION, 2005, 3361 : 223 - 231
[23] Evolving connectionist method for adaptive audiovisual speech recognition
Malcangi M.
Grew P.
[J]. Malcangi, Mario (malcangi@di.unimi.it), 2017, Springer Verlag (08) : 85 - 94
[24] ISOLATED WORD SPEECH RECOGNITION BASED ON CONNECTIONIST TECHNIQUES
WOODLAND, PC
[J]. BRITISH TELECOM TECHNOLOGY JOURNAL, 1990, 8 (02): : 61 - 66
[25] Boosting the performance of connectionist large vocabulary speech recognition
Cook, G
Robinson, T
[J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 1305 - 1308
[26] Continuous speech recognition using a hierarchical Bayesian model
Mouria-Beji, F
[J]. 2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING - VOL IV: SIGNAL PROCESSING FOR COMMUNICATIONS; VOL V: SIGNAL PROCESSING EDUCATION SENSOR ARRAY & MULTICHANNEL SIGNAL PROCESSING AUDIO & ELECTROACOUSTICS; VOL VI: SIGNAL PROCESSING THEORY & METHODS STUDENT FORUM, 2001, : 469 - 472
[27] A new phonetic model for continuous speech recognition systems
Fagundes, RDR
Corrêa, JS
Dumouchel, P
[J]. 2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 572 - 575
[28] CONTINUOUS SPEECH RECOGNITION
MORGAN, N
BOURLARD, H
[J]. IEEE SIGNAL PROCESSING MAGAZINE, 1995, 12 (03) : 25 - 42
[29] A DYNAMIC CONNECTIONIST MODEL FOR PHONEME RECOGNITION
ROBINSON, AJ
FALLSIDE, F
[J]. NEURAL NETWORKS FROM MODELS TO APPLICATIONS, 1989, : 541 - 550
[30] A connectionist model of phonological representation in speech perception
Gaskell, MG
Hare, M
Marslen-Wilson, WD
[J]. COGNITIVE SCIENCE, 1995, 19 (04) : 407 - 439

← 1 2 3 4 5 →