An Introduction to the Chinese Speech Recognition Front-End of the NICT/ATR Multi-Lingual Speech Translation System

被引：2

作者：

张劲松

Takatoshi Jitsuhiro

Hirofumi Yamamoto

胡新辉

Satoshi Nakamura

机构：

[1] Knowledge Creating Communication Research Center, National Institute of Information and Communications Technology, 2-2-2 Keihanna Science City, Kyoto 619-0288, Japan ATR Spoken Language Translation Research Laboratories, 2-2-2 Keihanna Science City, Kyoto

[2] ATR Knowledge Science Laboratories, 2-2-2 Keihanna Science City, Kyoto 619-0288, Japan

来源：

Tsinghua Science and Technology | 2008年 / 04期

关键词：

Chinese speech recognition; mutual information; phoneme set design; hidden Markov network; minimum description length; successive state splitting; multi-class composite N-grams;

D O I：

暂无

中图分类号：

TP391.42 [];

学科分类号：

0811 ; 081101 ; 081104 ; 1405 ;

摘要：

This paper introduces several important features of the Chinese large vocabulary continuous speech recognition system in the NICT/ATR multi-lingual speech-to-speech translation system. The features include: (1) a flexible way to derive an information rich phoneme set based on mutual information between a text corpus and its phoneme set; (2) a hidden Markov network acoustic model and a successive state split-ting algorithm to generate its model topology based on a minimum description length criterion; and (3) ad-vanced language modeling using multi-class composite N-grams. These features allow a recognition per-formance of 90% character accuracy in tourism related dialogue with a real time response speed.

引用

页码：545 / 552

页数：8

共 50 条

[1] An Introduction to the Chinese Speech Recognition Front-End of the NICT/ATR Multi-Lingual Speech Translation System
Knowledge Creating Communication Research Center, National Institute of Information and Communications Technology, 2-2-2 Keihanna Science City, Kyoto, 619-0288, Japan
不详
不详
[J]. Tsinghua Sci. Tech., 2008, 4 (545-552):
[2] NICT/ATR Chinese-Japanese-English Speech-to-Speech Translation System
Tohru Shimizu
Yutaka Ashikari
Eiichiro Sumita
张劲松
Satoshi Nakamura
[J]. Tsinghua Science and Technology, 2008, (04) : 540 - 544
[3] NICT/ATR Chinese-Japanese-English Speech-to-Speech Translation System
Shimizu, Tohru
Ashikari, Yutaka
Sumita, Eiichiro
Zhang, Jinsong
Nakamura, Satoshi
[J]. Tsinghua Science and Technology, 2008, 13 (04) : 540 - 544
[4] Development of the "VoiceTra" Multi-Lingual Speech Translation System
Matsuda, Shigeki
Hayashi, Teruaki
Ashikari, Yutaka
Shiga, Yoshinori
Kashioka, Hidenori
Yasuda, Keiji
Okuma, Hideo
Uchiyama, Masao
Sumita, Eiichiro
Kawai, Hisashi
Nakamura, Satoshi
[J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2017, E100D (04): : 621 - 632
[5] A Front-End Speech Enhancement System for Robust Automotive Speech Recognition
Wang, Haikun
Ye, Zhongfu
Chen, Jingdong
[J]. 2018 11TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2018, : 1 - 5
[6] Transfer Learning from Multi-Lingual Speech Translation Benefits Low-Resource Speech Recognition
Vanderreydt, Geoffroy
Remy, Francois
Demuynck, Kris
[J]. INTERSPEECH 2022, 2022, : 3053 - 3057
[7] A Reassigned Front-End for Speech Recognition
Tryfou, Georgina
Omologo, Maurizio
[J]. 2017 25TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2017, : 553 - 557
[8] A multi-lingual speech recognition system using a neural network approach
Chen, OTC
Chen, CY
Chang, HT
Hsu, FR
Yang, HL
Lee, YG
[J]. ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 1576 - 1581
[9] SERAB: A MULTI-LINGUAL BENCHMARK FOR SPEECH EMOTION RECOGNITION
Scheidwasser-Clow, Neil
Kegler, Mikolaj
Beckmann, Pierre
Cernak, Milos
[J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 7697 - 7701
[10] An automatic machine translation system for multi-lingual speech to Indian sign language
Dhanjal, Amandeep Singh
Singh, Williamjeet
[J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (03) : 4283 - 4321

← 1 2 3 4 5 →