Speaker-Dependent Bottleneck Features for Egyptian Arabic Speech Recognition

被引：0
|
作者：
Romanenko, Aleksei [1 ,2 ]
Mendelev, Valentin [1 ,2 ]
机构：
[1] ITMO Univ, St Petersburg, Russia
[2] Speech Technol Ctr Ltd, St Petersburg, Russia
来源：
SPEECH AND COMPUTER | 2016年 / 9811卷
关键词：
Arabic language; Keyword search; Low resources;
D O I：
10.1007/978-3-319-43958-7_75
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, several ways to improve a speech recognition system for the Egyptian dialect of Arabic language are presented. The research is based on the CALLHOME Egyptian Arabic corpus. We demonstrate the contribution of speaker-dependent bottleneck features trained on other languages and verify the possibility of application of a small Modern Standard Arabic (MSA) corpus to derive phonetic transcriptions. The systems obtained demonstrate good results as compared to those published before.
引用
下载
收藏
页码：620 / 626
页数：7
相关论文
共 50 条
  • [31] A Speaker-Dependent Deep Learning Approach to Joint Speech Separation and Acoustic Modeling for Multi-Talker Automatic Speech Recognition
    Tu, Yan-Hui
    Du, Jun
    Dai, Li-Rung
    Lee, Chin-Hui
    2016 10TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2016,
  • [32] CONNECTED-DIGIT SPEAKER-DEPENDENT SPEECH RECOGNITION USING A NEURAL NETWORK WITH TIME-DELAYED CONNECTIONS
    UNNIKRISHNAN, KP
    HOPFIELD, JJ
    TANK, DW
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1991, 39 (03) : 698 - 713
  • [33] Syntactic Features for Arabic Speech Recognition
    Kuo, Hong-Kwang Jeff
    Mangu, Lidia
    Emami, Ahmad
    Zitouni, Imed
    Lee, Young-Suk
    2009 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION & UNDERSTANDING (ASRU 2009), 2009, : 327 - 332
  • [34] Vowel Recognition from Continuous Articulatory Movements for Speaker-Dependent Applications
    Wang, Jun
    Green, Jordan R.
    Samal, Ashok
    Carrell, Tom D.
    2010 4TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATION SYSTEMS (ICSPCS), 2010,
  • [35] SPEAKER-DEPENDENT LARGE VOCABULARY WORD RECOGNITION USING THE SPLIT METHOD
    SUGAMURA, N
    FURUI, S
    REVIEW OF THE ELECTRICAL COMMUNICATIONS LABORATORIES, 1986, 34 (03): : 327 - 333
  • [36] Noise and Metadata Sensitive Bottleneck Features for Improving Speaker Recognition with Non-native Speech Input
    Qian, Yao
    Tao, Jidong
    Sitendermann-Oeft, David
    Evanini, Keelan
    Ivanov, Alexei V.
    Ramanarayanan, Vikram
    17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 3648 - 3652
  • [37] EXPLORING THE ROLE OF PHONETIC BOTTLENECK FEATURES FOR SPEAKER AND LANGUAGE RECOGNITION
    McLaren, Mitchell
    Ferrer, Luciana
    Lawson, Aaron
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5575 - 5579
  • [38] Low-SNR, Speaker-Dependent Speech Enhancement using GMMs and MFCCs
    Boucheron, Laura E.
    De Leon, Phillip L.
    13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 574 - 577
  • [39] Combining Missing-Feature Theory, Speech Enhancement and Speaker-Dependent/-Independent Modeling for Speech Separation
    Ming, Ji
    Hazen, Timothy J.
    Glass, James R.
    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 93 - +
  • [40] A Novel Weighted Dynamic Time Warping for Light Weight Speaker-Dependent Speech Recognition in Noisy and Bad Recording Conditions
    Zhang, Xianglilan
    Sun, Jiping
    Huang, Xuhui
    Luo, Zhigang
    MECHANICAL DESIGN AND POWER ENGINEERING, PTS 1 AND 2, 2014, 490-491 : 1347 - +
12345