THE IBM 2008 GALE ARABIC SPEECH TRANSCRIPTION SYSTEM

被引：9

作者：

Saon, George ^{[1
]}

Soltau, Hagen ^{[1
]}

Chaudhari, Upendra ^{[1
]}

Chu, Stephen ^{[1
]}

Kingsbury, Brian ^{[1
]}

Kuo, Hong-Kwang ^{[1
]}

Mangu, Lidia ^{[1
]}

Povey, Daniel ^{[2
]}

机构：

[1] IBM TJ Watson Res Ctr, Yorktown Hts, NY 10598 USA

[2] Microsoft Res, Redmond, WA USA

来源：

2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2010年

关键词：

Speech recognition;

D O I：

10.1109/ICASSP.2010.5495640

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 3.5 machine translation evaluation. Key advances compared to our Phase 2.5 system include improved discriminative training, the use of Subspace Gaussian Mixture Models (SGMM), neural network acoustic features, variable frame rate decoding, training data partitioning experiments, unpruned n-gram language models and neural network language models. These advances were instrumental in achieving a word error rate of 8.9% on the evaluation test set.

引用

页码：4378 / 4381

页数：4

共 50 条

[1] THE IBM 2009 GALE ARABIC SPEECH TRANSCRIPTION SYSTEM
Kingsbury, Brian
Soltau, Hagen
Saon, George
Chu, Stephen
Kuo, Hong-Kwang
Mangu, Lidia
Ravuri, Suman
Morgan, Nelson
Janin, Adam
2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 4672 - 4675
[2] Advances in Arabic Speech Transcription at IBM Under the DARPA GALE Program
Soltau, Hagen
Saon, George
Kingsbury, Brian
Kuo, Hong-Kwang Jeff
Mangu, Lidia
Povey, Daniel
Emami, Ahmad
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2009, 17 (05): : 884 - 894
[3] The IBM 2006 gale Arabic ASR system
Soltau, Hagen
Saon, George
2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 349 - +
[4] IBM GALE Mandarin transcription system
Zhang, Shilei
Shi, Qin
Qin, Yong
Liu, Wen
Chu, Stephen-M
Kuo, Hong-Kwang
Mangu, Lidia
Qinghua Daxue Xuebao/Journal of Tsinghua University, 2009, 49 (SUPPL. 1): : 1249 - 1253
[5] THE 2009 IBM GALE MANDARIN BROADCAST TRANSCRIPTION SYSTEM
Chu, Stephen M.
Povey, Daniel
Kuo, Hong-Kwang
Mangu, Lidia
Zhang, Shilei
Shi, Qin
Qin, Yong
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 4374 - 4377
[6] Recent advances in the IBM GALE Mandarin transcription system
Chu, Stephen M.
Kuo, Rong-kwang
Mangu, Lidia
Liu, Ji
Qin, Yong
Shi, Qin
Zhang, Shi Lei
Aronowitz, Hagai
2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4329 - 4332
[7] Advances in mandarin broadcast speech transcription at IBM under the DARPA GALE program
Qin, Yong
Shi, Qin
Liu, Yi Y.
Aronowitz, Hagai
Chu, Stephen M.
Kuo, Hong-Kwang
Zweig, Geoffrey
CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2006, 4274 : 410 - +
[8] The IBM BOLT Speech Transcription System
Thomas, Samuel
Saon, George
Kuo, Hong-Kwang
Mangu, Lidia
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 3150 - 3153
[9] The IBM mandarin broadcast speech transcription system
Chu, Stephen M.
Kuo, Hong-kwang
Liu, Yi Y.
Qin, Yong
Shi, Qin
Zweig, Geoffrey
2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PTS 1-3, 2007, : 345 - +
[10] The IBM 2007 speech transcription system for European parliamentary speeches
Ramabhadran, Bhuvana
Siohan, Olivier
Sethy, Abhinav
2007 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, VOLS 1 AND 2, 2007, : 472 - +

← 1 2 3 4 5 →