EI / SCOPUS / CSCD 收录

中文核心期刊

WANG Huan-liang, QIAN Yao, F. K. Soong, HAN Ji-qing. Noisy Chinese digit string speech recognition based on tone modeling[J]. ACTA ACUSTICA, 2007, 32(5): 454-460. DOI: 10.15949/j.cnki.0371-0025.2007.05.014
Citation: WANG Huan-liang, QIAN Yao, F. K. Soong, HAN Ji-qing. Noisy Chinese digit string speech recognition based on tone modeling[J]. ACTA ACUSTICA, 2007, 32(5): 454-460. DOI: 10.15949/j.cnki.0371-0025.2007.05.014

Noisy Chinese digit string speech recognition based on tone modeling

More Information
  • PACS: 
    • 43.70  (Speech production)
    • 43.60  (Acoustic signal processing)
  • Received Date: October 19, 2006
  • Revised Date: March 30, 2007
  • Available Online: August 05, 2022
  • It is attempted to utilize tone information to improve the performance of noisy Chinese digit string speech recognition. Multi-space probability distribution based HMM (MSD-HMM) is used to model the discontinuous tone features. The effect of noisy environment on tone features is analyzed and the feasibility of utilizing tone information to improve noisy speech recognition is discussed. Experimental results show that the proposed method can averagely obtain 17.2% relative reduction of digit error rate for the noisy data SNR from 5 dB to 20 dB, comparing with the method without tone information. The study concludes that it is effective to apply MSD-HMM based tone model to enhancing noisy Chinese digit string speech recognition.
  • Related Articles

    [1]ZHANG Qingqing, PAN Jielin, YAN Yonghong. Tonal articulatory feature-based acoustic modeling for Chinese Putonghua speech recognition[J]. ACTA ACUSTICA, 2010, 35(2): 254-260. DOI: 10.15949/j.cnki.0371-0025.2010.02.026
    [2]HUANG Hao, ZHU Jie. Tone model integration based on discriminative weight training for Putonghua speech recognition[J]. ACTA ACUSTICA, 2008, 33(1): 1-8. DOI: 10.15949/j.cnki.0371-0025.2008.01.016
    [3]ZHAO Li. Study on the Chinese continuous speech recognition under noise environments based on segmental unit input HMM[J]. ACTA ACUSTICA, 2002, 27(1): 59-61. DOI: 10.15949/j.cnki.0371-0025.2002.01.011
    [4]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
    [5]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
    [6]LIU Qingfeng, TENG Yongsheng, WANG Renhua. A speech synthesis system of digit strings with high quality and multi-channel real-time way[J]. ACTA ACUSTICA, 1999, 24(5): 510-515. DOI: 10.15949/j.cnki.0371-0025.1999.05.009
    [7]ZHAO Heming, ZHOU Xudong, JIN Yanqing, WENG Guirong. Overlapping speech pitch extraction and tone recognition based on wavelet transform[J]. ACTA ACUSTICA, 1999, 24(1): 87-93. DOI: 10.15949/j.cnki.0371-0025.1999.01.012
    [8]MA Xiaohui, FU Yuqing, LU Jiren, GONG Yifan. A study on recognition of continuous Chinese speech based on stochastic trajectory models[J]. ACTA ACUSTICA, 1997, 22(2): 176-181. DOI: 10.15949/j.cnki.0371-0025.1997.02.012
    [9]GUO Lixin, MO Fuyuan, LI Changli. A study of speech recognition of complete Chinese syllables based on continuous Gaussian Mixture HMM[J]. ACTA ACUSTICA, 1995, 20(5): 321-329. DOI: 10.15949/j.cnki.0371-0025.1995.05.001
    [10]GUAN Cun-tai, CHEN Yong-bin, WU Bo-xiu. A study on acoustic models of Chinese speech recognition system with whole Chinese syllables[J]. ACTA ACUSTICA, 1994, 19(5): 321-330. DOI: 10.15949/j.cnki.0371-0025.1994.05.001

Catalog

    Article Metrics

    Article views (44) PDF downloads (6) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return