A study of neural network Russian language models for automatic continuous speech recognition systems

被引：0
|
作者：
I. S. Kipyatkova
A. A. Karpov
机构：
[1] Russian Academy of Sciences,St. Petersburg Institute for Informatics and Automation
[2] State University of Aerospace Instrumentation,undefined
来源：
Automation and Remote Control | 2017年 / 78卷
关键词：
language models; neural networks; automatic speech recognition; Russian speech;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
We show the results of studying models of the Russian language constructed with recurrent artificial neural networks for systems of automatic recognition of continuous speech. We construct neural network models with different number of elements in the hidden layer and perform linear interpolation of neural network models with the baseline trigram language model. The resulting models were used at the stage of rescoring the N best list. In our experiments on the recognition of continuous Russian speech with extra-large vocabulary (150 thousands of word forms), the relative reduction in the word error rate obtained after rescoring the 50 best list with the neural network language models interpolated with the trigram model was 14%.
引用
收藏
页码：858 / 867
页数：9
相关论文
共 50 条
  • [1] A study of neural network Russian language models for automatic continuous speech recognition systems
    Kipyatkova, I. S.
    Karpov, A. A.
    AUTOMATION AND REMOTE CONTROL, 2017, 78 (05) : 858 - 867
  • [2] BIDIRECTIONAL RECURRENT NEURAL NETWORK LANGUAGE MODELS FOR AUTOMATIC SPEECH RECOGNITION
    Arisoy, Ebru
    Sethy, Abhinav
    Ramabhadran, Bhuvana
    Chen, Stanley
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 5421 - 5425
  • [3] SEMANTIC WORD EMBEDDING NEURAL NETWORK LANGUAGE MODELS FOR AUTOMATIC SPEECH RECOGNITION
    Audhkhasi, Kartik
    Sethy, Abhinav
    Ramabhadran, Bhuvana
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5995 - 5999
  • [4] Latent Words Recurrent Neural Network Language Models for Automatic Speech Recognition
    Masumura, Ryo
    Asami, Taichi
    Oba, Takanobu
    Sakauchi, Sumitaka
    Ito, Akinori
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2019, E102D (12) : 2557 - 2567
  • [5] Emotional Speech Recognition of Holocaust Survivors with Deep Neural Network Models for Russian Language
    Bukreeva, Liudmila
    Guseva, Daria
    Dolgushin, Mikhail
    Evdokimova, Vera
    Obotnina, Vasilisa
    SPEECH AND COMPUTER, SPECOM 2023, PT I, 2023, 14338 : 68 - 76
  • [6] Recurrent Neural Network-based Language Modeling for an Automatic Russian Speech Recognition System
    Kipyatkova, Irina
    Karpov, Alexey
    2015 ARTIFICIAL INTELLIGENCE AND NATURAL LANGUAGE AND INFORMATION EXTRACTION, SOCIAL MEDIA AND WEB SEARCH FRUCT CONFERENCE (AINL-ISMW FRUCT), 2015, : 33 - 38
  • [7] Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition
    Chen, Xie
    Liu, Xunying
    Wang, Yongqiang
    Gales, Mark J. F.
    Woodland, Philip C.
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2016, 24 (11) : 2146 - 2157
  • [8] Empirical study of neural network language models for Arabic speech recognition
    Emami, Ahmad
    Mangu, Lidia
    2007 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, VOLS 1 AND 2, 2007, : 147 - 152
  • [9] Neural Error Corrective Language Models for Automatic Speech Recognition
    Tanaka, Tomohiro
    Masumura, Ryo
    Masataki, Hirokazu
    Aono, Yushi
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 401 - 405
  • [10] Converting Neural Network Language Models into Back-off Language Models for Efficient Decoding in Automatic Speech Recognition
    Arisoy, Ebru
    Chen, Stanley F.
    Ramabhadran, Bhuvana
    Sethy, Abhinav
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2014, 22 (01) : 184 - 192
12345