MLP BASED PHONEME DETECTORS FOR AUTOMATIC SPEECH RECOGNITION

被引：0
|
作者：
Thomas, Samuel [1 ]
Patrick Nguyen
Zweig, Geoffrey
Hermansky, Hynek [1 ]
机构：
[1] Johns Hopkins Univ, Baltimore, MD 21218 USA
来源：
2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2011年
关键词：
Phoneme Posteriors; Multi-layer Perceptrons; Segmental Conditional Random Fields;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
Phoneme posterior probabilities estimated using Multi-Layer Perceptrons (MLPs) are extensively used both as acoustic scores and features for speech recognition. In this paper we explore a different application of these posteriors - as phonetic event detectors for speech recognition. We show how these detectors can be built to reliably capture phonetic events in the acoustic signal by integrating both acoustic and phonetic information about sound classes. These event detectors are used along with Segmental Conditional Random Fields (SCRFs) to improve the performance of speech recognition systems on the Broadcast News task.
引用
收藏
页码：5024 / 5027
页数：4
相关论文
共 50 条
  • [1] The Gamma MLP for speech phoneme recognition
    Lawrence, S
    Tsoi, AC
    Back, AD
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 8: PROCEEDINGS OF THE 1995 CONFERENCE, 1996, 8 : 785 - 791
  • [2] PHONEME SELECTION FOR STUDIES IN AUTOMATIC SPEECH RECOGNITION
    SHOUP, JE
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1962, 34 (04): : 397 - &
  • [3] Phoneme Confusions in Human and Automatic Speech Recognition
    Meyer, Bernd T.
    Waechter, Matthias
    Brand, Thomas
    Kollmeier, Birger
    [J]. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 2740 - 2743
  • [4] A Comprehensive Examination of Phoneme Recognition in Automatic Speech Recognition Systems
    Bhatt, Shobha
    Bansal, Shweta
    Kumar, Ankit
    Pandey, Saroj Kumar
    Ojha, Manoj Kumar
    Singh, Kamred Udham
    Chakraborty, Sanjay
    Singh, Teekam
    Swarup, Chetan
    [J]. TRAITEMENT DU SIGNAL, 2023, 40 (05) : 1997 - 2008
  • [5] Automatic Phoneme Border Detection to Improve Speech Recognition
    Sergio, Suarez-Guerra
    Cristian-Remington, Juarez-Murillo
    Jose Luis, Oropeza-Rodriguez
    [J]. ADVANCES IN ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, MICAI 2015, PT I, 2015, 9413 : 127 - 135
  • [6] DNN-based automatic speech recognition as a model for human phoneme perception
    Exter, Mats
    Meyer, Bernd T.
    [J]. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 615 - 619
  • [7] Automatic Fongbe Phoneme Recognition From Spoken Speech Signal
    Laleye, Frejus A. A.
    Ezin, Eugene C.
    Motamed, Cina
    [J]. ICINCO: PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, VOL 1, 2016, : 102 - 109
  • [8] The efficient incorporation of MLP features into automatic speech recognition systems
    Park, J.
    Diehl, F.
    Gales, M. J. F.
    Tomalin, M.
    Woodland, P. C.
    [J]. COMPUTER SPEECH AND LANGUAGE, 2011, 25 (03): : 519 - 534
  • [9] Building Automatic Speech Recognition Systems for Moroccan Dialect: A Phoneme-Based Approach
    Abderrahim Ezzine
    Naouar Laaidi
    Ouissam Zealouk
    Hassan Satori
    [J]. SN Computer Science, 5 (6)
  • [10] Contribution from the accuracy of phoneme recognition to the quality of automatic recognition of Russian speech
    Karpukhin I.A.
    [J]. Moscow University Computational Mathematics and Cybernetics, 2016, 40 (2) : 89 - 95
12345