Hybrid language models for out of vocabulary word detection in large vocabulary conversational speech recognition

被引：0

作者：

Yazgan, A ^{[1
]}

Saraclar, M ^{[1
]}

机构：

[1] Johns Hopkins Univ, Ctr Language & Speech Proc, Baltimore, MD 21218 USA

来源：

2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING | 2004年

关键词：

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this paper, we propose a method for out-of-vocabulary (OOV) word detection and taking a step toward open vocabulary automatic speech recognition. The proposed method uses a hybrid language model combining words and subword units such as phones or syllables. We describe a detection algorithm based on the posterior count of the OOV words given the hybrid model, and compare it to using the posterior probability of the best word string given a conventional word only model. Experimental results on the Switchboard corpus are presented for different vocabulary sizes. The new method yields a gain of over 10% in OOV word detection. In addition, a modest number of the OOV word pronunciations are found correctly.

引用

页码：745 / 748

页数：4

共 50 条

[21] Language identification through large vocabulary continous speech recognition
Lim, BP
Li, HZ
Chen, Y
[J]. 2004 INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2004, : 49 - 52
[22] A large vocabulary continuous speech recognition system for Persian language
Sameti, Hossein
Veisi, Hadi
Bahrani, Mohammad
Babaali, Bagher
Hosseinzadeh, Khosro
[J]. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2011, : 1 - 12
[23] A multispan language modeling framework for large vocabulary speech recognition
Bellegarda, JR
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1998, 6 (05): : 456 - 467
[24] LARGE-VOCABULARY SPEECH RECOGNITION - A SYSTEM FOR THE ITALIAN LANGUAGE
DORTA, P
FERRETTI, M
MARTELLI, A
MELECRINIS, S
SCARCI, S
VOLPI, G
[J]. IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 1988, 32 (02) : 217 - 226
[25] LISTEN, ATTEND AND SPELL: A NEURAL NETWORK FOR LARGE VOCABULARY CONVERSATIONAL SPEECH RECOGNITION
Chan, William
Jaitly, Navdeep
Quoc Le
Vinyals, Oriol
[J]. 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 4960 - 4964
[26] Spoken language identification using large vocabulary speech recognition
Bell Lab, Murray Hill, United States
[J]. Int Conf Spoken Lang Process ICSLP Proc, 1600, (1780-1783):
[27] Tree-structured models of parameter dependence for rapid adaptation in large vocabulary conversational speech recognition
Kannan, A
Khudanpur, S
[J]. ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 769 - 772
[28] Out-of-vocabulary word rejection algorithm in Korean variable vocabulary word recognition
Moon, KS
Kim, YJ
Kim, HR
Chung, JH
[J]. ISCAS 2000: IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS - PROCEEDINGS, VOL V: EMERGING TECHNOLOGIES FOR THE 21ST CENTURY, 2000, : 53 - 56
[29] Extensions to the word graph method for large vocabulary continuous speech recognition
Ney, H
Ortmanns, S
Lindam, I
[J]. 1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 1791 - 1794
[30] Posterior-based Out of Vocabulary Word Detection in Telephone Speech
Kombrink, Stefan
Burget, Lukas
Matejka, Pavel
Karafiat, Martin
Hermansky, Hynek
[J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 84 - 87

← 1 2 3 4 5 →