N-gram Language Models in JLASER Neural Network Speech Recognizer

被引：0

作者：

Konopik, Miloslav ^{[1
]}

Habernal, Ivan ^{[1
]}

Brychcin, Tomas ^{[1
]}

机构：

[1] Univ W Bohemia, Dept Comp Sci & Engn, Plzen 30614, Czech Republic

来源：

2010 INTERNATIONAL CONFERENCE ON APPLIED ELECTRONICS | 2010年

关键词：

D O I：

暂无

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：

In our recent research we have discovered that neural networks can be more efficient in speech recognition than the state of the art approach based on Gaussian mixtures. This statement is valid only for small corpora, however, many applications do not require a huge recognition vocabulary. In this article we describe our speech recognizer - called JLASER - based on neural networks. We also show the effect of n-gram language models applied to the JLASER recognizer.

引用

页码：167 / 170

页数：4

共 50 条

[21] LARGE MARGIN ESTIMATION OF N-GRAM LANGUAGE MODELS FOR SPEECH RECOGNITION VIA LINEAR PROGRAMMING
Magdin, Vladimir
Jiang, Hui
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 5398 - 5401
[22] N-gram language models for Polish language. Basic concepts and applications in automatic speech recognition systems
Rapp, Bartosz
2008 INTERNATIONAL MULTICONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY (IMCSIT), VOLS 1 AND 2, 2008, : 295 - 298
[23] Language modeling by string pattern N-gram for Japanese speech recognition
Ito, A
Kohda, M
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 490 - 493
[24] N-gram language models for offline handwritten text recognition
Zimmermann, M
Bunke, H
NINTH INTERNATIONAL WORKSHOP ON FRONTIERS IN HANDWRITING RECOGNITION, PROCEEDINGS, 2004, : 203 - 208
[25] Variable-length category n-gram language models
Univ of Cambridge, Cambridge, United Kingdom
Comput Speech Lang, 1 (99-124):
[26] TOPIC N-GRAM COUNT LANGUAGE MODEL ADAPTATION FOR SPEECH RECOGNITION
Haidar, Md. Akmal
O'Shaughnessy, Douglas
2012 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2012), 2012, : 165 - 169
[27] N-gram Counts and Language Models from the Common Crawl
Buck, Christian
Heafield, Kenneth
van Ooyen, Bas
LREC 2014 - NINTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2014, : 3579 - 3584
[28] Character n-Gram Embeddings to Improve RNN Language Models
Takase, Sho
Suzuki, Jun
Nagata, Masaaki
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 5074 - 5082
[29] On the N-gram Approximation of Pre-trained Language Models
Krishnan, Aravind
Alabi, Jesujoba O.
Klakow, Dietrich
INTERSPEECH 2023, 2023, : 371 - 375
[30] Learning N-gram Language Models from Uncertain Data
Kuznetsov, Vitaly
Liao, Hank
Mohri, Mehryar
Riley, Michael
Roark, Brian
17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 2323 - 2327

← 1 2 3 4 5 →