Simplified Scoring Methods in HMM Based Speech Recognition

被引：2
|
作者：
Paramonov, Pavel [1 ]
Sutula, Nadezhda [1 ]
机构：
[1] Natl Res Univ Moscow Power Engn Inst, Inst Automat & Comp Engn, Moscow, Russia
来源：
2014 INTERNATIONAL CONFERENCE ON SOFT COMPUTING & MACHINE INTELLIGENCE ISCMI 2014 | 2014年
关键词：
Hidden Markov Models; speech recognition; forward algorithm; isolated words recognition;
D O I：
10.1109/ISCMI.2014.32
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 we present two ways to simplify scoring in Hidden Markov Models (HMM) based speech recognition in order to reduce it's computational complexity. We tested proposed approaches on Russian words recognition and compared results with those that gave recognition using conventional forward algorithm.
引用
收藏
页码：154 / 156
页数：3
相关论文
共 50 条
  • [21] Speech emotion recognition based on a hybrid of HMM/ANN
    Mao, Xia
    Zhang, Bing
    Luo, Yi
    PROCEEDINGS OF THE 7TH WSEAS INTERNATIONAL CONFERENCE ON APPLIED INFORMATICS AND COMMUNICATIONS, 2007, : 369 - 372
  • [22] A Research on HMM based Speech Recognition in Spoken English
    Wang, Na
    Zhang, Xiaohong
    Sharma, Ashutosh
    RECENT ADVANCES IN ELECTRICAL & ELECTRONIC ENGINEERING, 2021, 14 (06) : 617 - 626
  • [23] Uzbek speech commands recognition and implementation based on HMM
    Ugli, Shukurov Kamoliddin Elbobo
    Ugli, Kholdorov Shokhrukhmirzo Imomali
    Ugli, Khasanov Umidjon Komiljon
    2020 IEEE 14TH INTERNATIONAL CONFERENCE ON APPLICATION OF INFORMATION AND COMMUNICATION TECHNOLOGIES (AICT2020), 2020,
  • [24] The hybrid model of speech recognition based on HMM and HMMNN
    Wang Sheguo
    Tong Jianing
    Yuan Yujin
    2009 INTERNATIONAL CONFERENCE ON E-BUSINESS AND INFORMATION SYSTEM SECURITY, VOLS 1 AND 2, 2009, : 926 - +
  • [25] HMM based recognition of Chinese tones in continuous speech
    Cheng, ML
    Cheng, XM
    Zhao, L
    PROCEEDINGS OF 2003 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS & SIGNAL PROCESSING, PROCEEDINGS, VOLS 1 AND 2, 2003, : 916 - 919
  • [26] HMM BASED ISOLATED WORD NEPALI SPEECH RECOGNITION
    Ssarma, Manish K.
    Gajurel, Avaas
    Pokhrel, Anup
    Joshi, Basanta
    PROCEEDINGS OF 2017 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC), VOL 1, 2017, : 71 - 76
  • [27] Russian Speech Recognition System Design Based on HMM
    Ma Yanzhou
    Yi Mianzhu
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON LOGISTICS, ENGINEERING, MANAGEMENT AND COMPUTER SCIENCE, 2014, 101 : 377 - 380
  • [28] Contaminated speech training methods for robust DNN-HMM distant speech recognition
    Ravanelli, Mirco
    Omologo, Maurizio
    16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 756 - 760
  • [29] Confidence scoring for accurate HMM-based speech recognition by using monophone-level normalization based on subspace method
    Ghulam, M
    Sato, T
    Fukuda, T
    Nitta, T
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2003, E86D (03): : 430 - 437
  • [30] Confidence scoring for accurate HMM-based speech recognition by using monophone-level normalization based on subspace method
    Ghulam, Muhammad
    Sato, Takaharu
    Fukuda, Takashi
    Nitta, Tsuneo
    IEICE Transactions on Information and Systems, 2003, E86-D (03) : 430 - 437
12345