Automatic Speech Recognition Used for Intelligibility Assessment of Text-to-Speech Systems

被引：0
|
作者：
Vich, Robert [1 ]
Nouza, Jan [2 ]
Vondra, Martin [1 ]
机构：
[1] Acad Sci Czech Republ, Inst Photon & Elect, Chaberska 57, CZ-18251 Prague 8, Czech Republic
[2] Techn Univ Liberec, Inst Informat Technol & Elect, CZ-46117 Libechov, Czech Republic
来源：
VERBAL AND NONVERBAL FEATURES OF HUMAN-HUMAN AND HUMAN-MACHINE INTERACTIONS | 2008年 / 5042卷
关键词：
Speech recognition; speech synthesis; speech assessment;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Speech intelligibility is the most important parameter in evaluation of speech quality. In the contribution, a new objective intelligibility assessment of general speech processing algorithms is proposed. It is based on automatic recognition methods developed for discrete and fluent speech processing. The idea is illustrated on two case studies: a) comparison of listening evaluation of Czech rhyme tests with automatic discrete speech recognition and b) automatic continuous speech recognition of general topic Czech texts read by professional and nonprofessional speakers vs. the same texts generated by several Czech Text-to-Speech systems. The aim of the proposed approach is fast and objective intelligibility assessment of Czech Text-to-Speech systems, which include male and female voices and a voice conversion module.
引用
收藏
页码：136 / +
页数：2
相关论文
共 50 条
  • [1] Method of intelligibility testing for text-to-speech systems
    Sheffield, E
    Polizzi, P
    [J]. PROCEEDINGS OF THE FIFTH JOINT CONFERENCE ON INFORMATION SCIENCES, VOLS 1 AND 2, 2000, : A862 - A865
  • [2] Text-To-Speech Intelligibility across Speech Rates
    Syrdal, Ann K.
    Bunnell, H. Timothy
    Hertz, Susan R.
    Mishra, Taniya
    Spiegel, Murray
    Bickley, Corine
    Rekart, Deborah
    Makashay, Matthew J.
    [J]. 13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 622 - 625
  • [3] Objective Intelligibility Assessment of Text-to-Speech Systems Through Utterance Verification
    Ullmann, Raphael
    Rasipuram, Ramya
    Magimai-Dossi, Mathew
    Bourlard, Herve
    [J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 3501 - 3505
  • [4] INTELLIGIBILITY OF SPEECH PRODUCED BY TEXT-TO-SPEECH SYSTEMS IN GOOD AND TELEPHONIC CONDITIONS
    DELOGU, C
    PAOLONI, A
    RIDOLFI, P
    VAGGES, K
    [J]. ACTA ACUSTICA, 1995, 3 (01): : 89 - 96
  • [5] Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition
    Ni, Junrui
    Wang, Liming
    Gao, Heting
    Qian, Kaizhi
    Zhang, Yang
    Chang, Shiyu
    Hasegawa-Johnson, Mark
    [J]. INTERSPEECH 2022, 2022, : 461 - 465
  • [6] Comparing intelligibility and recognition memory of human and text-to-speech voices
    Aoki, Nicholas
    Zellou, Georgia
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2023, 153 (03):
  • [7] Automatic Syllabification for Danish Text-to-Speech Systems
    Beck, Jeppe
    Braga, Daniela
    Nogueira, Joao
    Dias, Miguel Sales
    Coelho, Luis
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1291 - 1294
  • [8] Segmental intelligibility of four currently used text-to-speech synthesis methods
    Venkatagiri, HS
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2003, 113 (04): : 2095 - 2104
  • [9] PERCEPTION OF SYNTHETIC SPEECH PRODUCED AUTOMATICALLY BY RULE - INTELLIGIBILITY OF 8 TEXT-TO-SPEECH SYSTEMS
    GREENE, BG
    LOGAN, JS
    PISONI, DB
    [J]. BEHAVIOR RESEARCH METHODS INSTRUMENTS & COMPUTERS, 1986, 18 (02): : 100 - 107
  • [10] CrossASR: Efficient Differential Testing of Automatic Speech Recognition via Text-To-Speech
    Asyrofi, Muhammad Hilmi
    Thung, Ferdian
    Lo, David
    Jiang, Lingxiao
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE MAINTENANCE AND EVOLUTION (ICSME 2020), 2020, : 640 - 650
12345