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

[1] Shortlist B: A Bayesian model of continuous speech recognition
Norris, Dennis
McQueen, James M.
[J]. PSYCHOLOGICAL REVIEW, 2008, 115 (02) : 357 - 395
[2] Continuous speech recognition with a robust connectionist/Markovian hybrid model
Trentin, E
Gori, M
[J]. ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS, 2001, 2130 : 577 - 582
[3] CONNECTIONIST APPROACHES TO LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
SAWAI, H
MINAMI, Y
MIYATAKE, M
WAIBEL, A
SHIKANO, K
[J]. IEICE TRANSACTIONS ON COMMUNICATIONS ELECTRONICS INFORMATION AND SYSTEMS, 1991, 74 (07): : 1834 - 1844
[4] CONTINUOUS SPEECH RECOGNITION BY CONNECTIONIST STATISTICAL-METHODS
BOURLARD, H
MORGAN, N
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (06): : 893 - 909
[5] Connectionist language modeling for large vocabulary continuous speech recognition
Schwenk, H
Gauvain, JL
[J]. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 765 - 768
[6] Committees of RBFN - A novel connectionist model for speech recognition
Meenakshisundaram, S
Woo, WL
Dlay, SS
[J]. Proceedings of the Eighth IASTED International Conference on Artificial Intelligence and Soft Computing, 2004, : 300 - 304
[7] Connectionist Approach for Emission Probability Estimation in Malayalam Continuous Speech Recognition
Mohamed, Anuj
Nair, K. N. Ramachandran
[J]. INFORMATION SYSTEMS DESIGN AND INTELLIGENT APPLICATIONS, VOL 1, 2015, 339 : 343 - 351
[8] The time-sliced paradigm - A connectionist method for continuous speech recognition
Kirschning, I
Tomabechi, H
Koyama, M
Aoe, JI
[J]. INFORMATION SCIENCES, 1996, 93 (1-2) : 133 - 158
[9] Bridging automatic speech recognition. and psycholinguistics: Extending Shortlist to an end-to-end model of human speech recognition
Scharenborg, O
ten Bosch, L
Boves, L
Norris, D
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2003, 114 (06): : 3032 - 3035
[10] CONTINUOUS SPEECH RECOGNITION - HIDDEN MARKOV-MODELS VS THE CONNECTIONIST HOPE
BOURLARD, HA
[J]. TWENTY-THIRD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1 AND 2: CONFERENCE RECORD, 1989, : 331 - 335

← 1 2 3 4 5 →