Hybrid Model of Continuous Hidden Markov Model and Multi-Layer Perceptron in Speech Recognition

被引：2
|
作者：
Zhang, Peiling [1 ]
Li, Hui [1 ]
机构：
[1] Henan Polytech Univ, Coll Elect Engn & Automat, Jiaozuo 454003, Peoples R China
来源：
ICICTA: 2009 SECOND INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTATION TECHNOLOGY AND AUTOMATION, VOL II, PROCEEDINGS | 2009年
关键词：
mandarin digit speech recognition; continuous hidden markov model; multi-layer perceptron;
D O I：
10.1109/ICICTA.2009.252
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In order to overcome shortcomings of basic hidden markov model (HMM), a hybrid model of multi-layer perceptron (MLP) and continuous hidden markov model (CHMM) is presented which bases on basic HMM. In this hybrid mode, MLP calculates each state's output probability instead of CHMM. The main purpose of this model is to improve the recognition ratio of CHMM by means of the strong of MLP's nonlinear predictive capability. Speaker independent mandarin digit speech recognition which based on the hybrid models is realized. Experimental results show that the hybrid model is efficiency and has higher recognition ratio than basic CHMM.
引用
收藏
页码：62 / 65
页数：4
相关论文
共 50 条
  • [1] A Hybrid Segmental Neural Net/Hidden Markov Model System for Continuous Speech Recognition
    Zavaliagkos, G.
    Zhao, Y.
    Schwartz, R.
    Makhoul, J.
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1994, 2 (01): : 151 - 160
  • [2] Hybrid support vector machine hidden Markov model approach for continuous speech recognition
    Chakrabartty, S
    Singh, G
    Cauwenberghs, G
    PROCEEDINGS OF THE 43RD IEEE MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS I-III, 2000, : 828 - 831
  • [3] Speech Emotion Recognition Using Multi-Layer Perceptron Classifier
    Yuan, Xiaochen
    Wong, Wai Pang
    Lam, Chan Tong
    2022 IEEE 10TH INTERNATIONAL CONFERENCE ON INFORMATION, COMMUNICATION AND NETWORKS (ICICN 2022), 2022, : 644 - 648
  • [4] Phoneme segmentation of continuous speech using multi-layer perceptron
    Suh, Y
    Lee, Y
    ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 1297 - 1300
  • [5] Ozone Modeling in an urban atmosphere using artificial neural network. hybrid hidden markov model/multi-layer perceptron. the NEUROZONE model.
    Rynkiewicz, J
    Dutot, AL
    Steiner, F
    AIR POLLUTION MODELLING AND SIMULATION, PROCEEDINGS, 2002, : 537 - 543
  • [6] Tone recognition of Vietnamese continuous speech using hidden Markov model
    Quang, Nguyen Hong
    Pascal, Nocera
    Eric, Castelli
    Van Loan, Trinh
    2008 SECOND INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND ELECTRONICS, 2008, : 233 - +
  • [7] Speech recognition using hybrid hidden Markov model and NN classifier
    Kundu, A.
    Bayya, A.
    International Journal of Speech Technology, 1998, 2 (03): : 227 - 240
  • [8] Speech recognition using hybrid hidden Markov model and NN classifier
    Kundu A.
    Bayya A.
    International Journal of Speech Technology, 1998, 2 (3) : 227 - 240
  • [9] Multi-Layer Hidden Markov Model Based Intrusion Detection System
    Zegeye, Wondimu K.
    Dean, Richard A.
    Moazzami, Farzad
    MACHINE LEARNING AND KNOWLEDGE EXTRACTION, 2019, 1 (01): : 265 - 286
  • [10] Belief Hidden Markov Model for Speech Recognition
    Jendoubi, Siwar
    Ben Yaghlane, Boutheina
    Martin, Arnaud
    2013 5TH INTERNATIONAL CONFERENCE ON MODELING, SIMULATION AND APPLIED OPTIMIZATION (ICMSAO), 2013,
12345