EI / SCOPUS / CSCD 收录

中文核心期刊

WANG Chengyou, TANG Shuqi, LIANG Diannong, CHEN Huihuang, TANG Chaojing. Methods for combining the information of various features in speech recognition[J]. ACTA ACUSTICA, 1997, 22(2): 111-115. DOI: 10.15949/j.cnki.0371-0025.1997.02.003
Citation: WANG Chengyou, TANG Shuqi, LIANG Diannong, CHEN Huihuang, TANG Chaojing. Methods for combining the information of various features in speech recognition[J]. ACTA ACUSTICA, 1997, 22(2): 111-115. DOI: 10.15949/j.cnki.0371-0025.1997.02.003

Methods for combining the information of various features in speech recognition

More Information
  • PACS: 
    • 43.38  (换能器, 声学器件)
  • Received Date: February 04, 1996
  • Revised Date: April 14, 1996
  • Available Online: August 01, 2022
  • In studies of speech recognition based on features, it is often discovered that the recognition performance of some features for some utterances is better than for the others while the other features have opposite effects. They have, to some extent, the complementary relation in the recognition of some utterances. Based on HMM which is now widely used in speech recognition studies, three efficient methods for combining multiple complementary features to improve the recognition performance of HMM are presented in this paper. They are defined as the maximum parameter method, the all parameter method and the most reliable parameter method. The three methods respectively improve the performance in multi-speaker Chinese digit DHMM/VQ recognition from 89% to 92.3%, 95.7%, 94.3%. This paper describes the three methods and gives experimental results and analysis in multi-speaker Chinese digit DHMM/VQ recognition in detail.
  • Related Articles

    [1]GAO Changfeng, CHENG Gaofeng, ZHANG Pengyuan. Consistency self-supervised learning method for robust automatic speech recognition[J]. ACTA ACUSTICA, 2023, 48(3): 578-587. DOI: 10.15949/j.cnki.0371-0025.2023.03.008
    [2]CHEN Bin, CHEN Qi, ZHANG Lianhai, QU Dan, LI Bicheng. A speech recognition method based on complementary system generation and combination[J]. ACTA ACUSTICA, 2016, 41(1): 125-134. DOI: 10.15949/j.cnki.0371-0025.2016.01.015
    [3]YIN Hui, XIE Xiang, KUANG Jingming. Acoustic features based on auditory model and adaptive fractional Fourier transform for speech recognition[J]. ACTA ACUSTICA, 2012, 37(1): 97-103. DOI: 10.15949/j.cnki.0371-0025.2012.01.011
    [4]SUN Yanqing, ZHANG Qingqing, ZHOU Yu, ZHAO Qingwei, YAN Yonghong. Analysis and subset selection of articulatory features for speech recognition confidence measures[J]. ACTA ACUSTICA, 2011, 36(3): 339-348. DOI: 10.15949/j.cnki.0371-0025.2011.03.005
    [5]ZHANG Jun, WEI Gang, YU Hua. Robust multi-stream speech recognition based on weighting the output probabilities of feature components[J]. ACTA ACUSTICA, 2008, 33(2): 102-108. DOI: 10.15949/j.cnki.0371-0025.2008.02.015
    [6]JIANG Wenjian, WEI Gang. A new feature extraction method for noisy speech recognition based on masking model[J]. ACTA ACUSTICA, 2001, 26(6): 516-520. DOI: 10.15949/j.cnki.0371-0025.2001.06.007
    [7]ZHAO Li, ZOU Cairong, WU Zhenyang. Study on the integration of speech and language processing in Recognition of Chinese Continuous Speech[J]. ACTA ACUSTICA, 2001, 26(1): 73-78. DOI: 10.15949/j.cnki.0371-0025.2001.01.013
    [8]HAN Jiang, YIN Baolin. A model for speech recognition based on joint modeling of frame-based and segmental features[J]. ACTA ACUSTICA, 2000, 25(2): 182-190. DOI: 10.15949/j.cnki.0371-0025.2000.02.016
    [9]ZHAO Qingwei, XIAO Xi, WANG Zuoying, LU Dajin. A study of duration in continuous speech recognition based on DDBHMM[J]. ACTA ACUSTICA, 2000, 25(2): 175-181. DOI: 10.15949/j.cnki.0371-0025.2000.02.015
    [10]WANG Chengyou, TANG Shuqi, LIANG Diannong. The influence of noise on the speech recognition performance using the methods for the combination of features[J]. ACTA ACUSTICA, 1997, 22(3): 282-285. DOI: 10.15949/j.cnki.0371-0025.1997.03.012

Catalog

    Article Metrics

    Article views (57) PDF downloads (6) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return