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

[21] The 2010 CMU GALE Speech-to-Text System
Metze, Florian
Hsiao, Roger
Jin, Qin
Nallasamy, Udhyakumar
Schultz, Tanja
11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, 2010, : 1501 - 1504
[22] Advances in speech transcription at IBM under the DARPA EARS program
Chen, Stanley F.
Kingsbury, Brian
Mangu, Lidia
Povey, Daniel
Saon, George
Soltau, Hagen
Zweig, Geoffrey
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (05): : 1596 - 1608
[23] Arabic broadcast news transcription system
Alghamdi, Mansour
Elshafei, Moustafa
Al-Muhtaseb, Husni
INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2007, 10 (04) : 183 - 195
[24] Arabic automatic segmentation system and its application for arabic speech recognition system
Nofal, M
Abdel-Raheem, E
Kader, NSA
Proceedings of the 46th IEEE International Midwest Symposium on Circuits & Systems, Vols 1-3, 2003, : 697 - 700
[25] Arabic ASR and MT integration for GALE
Al-Onaizan, Yaser
Mangu, Lidia
2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 1285 - +
[26] ARABIC SOFTWARE FOR THE IBM
RIPPIN, A
COMPUTERS AND THE HUMANITIES, 1991, 25 (06): : 445 - 448
[27] COSEGMENTATION IN THE IBM TEXT-TO-SPEECH SYSTEM
PICKERING, JB
PROCEEDINGS : INSTITUTE OF ACOUSTICS, VOL 8, PART 7: SPEECH & HEARING, 1986, 8 : 385 - 392
[28] Speech Recognition System of Arabic Alphabet Based on a Telephony Arabic Corpus
Alotaibi, Yousef Ajami
Alghamdi, Mansour
Alotaiby, Fabad
IMAGE AND SIGNAL PROCESSING, PROCEEDINGS, 2010, 6134 : 122 - +
[29] IBM GALE中文识别系统
张世磊
施勤
秦勇
刘文
CHU StephenM
KUO HongKwang
MANGU Lidia
清华大学学报(自然科学版), 2009, 49(S1) (自然科学版) : 1249 - 1253
[30] IBM GALE中文识别系统
张世磊
施勤
秦勇
刘文
CHU StephenM
KUO Hong-Kwang
MANGU Lidia
清华大学学报(自然科学版), 2009, 49 (S1) : 1249 - 1253

← 1 2 3 4 5 →