HMM-Based Cue Parameters Estimation for Speech Enhancement

被引:0
|
作者
Deng, Feng [1 ]
Bao, Chang-chun [1 ]
Jia, Mao-shen [1 ]
机构
[1] Beijing Univ Technol, Sch Elect Informat & Control Engn, Speech & Audio Signal Proc Lab, Beijing 100124, Peoples R China
来源
2016 10TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP) | 2016年
基金
中国国家自然科学基金;
关键词
speech enhancement; HMM; cue parameters; priori information; NOISE;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this paper, a hidden Markov model (HMM)-based cue parameters estimation method for single-channel speech enhancement is proposed, in which the cue parameters of binaural cue coding (BCC) are applied to single-channel speech enhancement system successfully. First, the clean speech and noise signals are considered as the left and right channels of stereo signal, respectively; and the noisy speech is treated as the down-mixed mono signal of BCC method. According to the clean speech and noise data set and the corresponding noisy speech data set, the clean cue parameters and pre-enhanced cue parameters are extracted, respectively. Then the cue HMM is trained offline, which exploits the a priori information about the clean cue parameters and the pre-enhanced cue parameters for speech enhancement. Next, using the trained cue HMM, the clean cue parameters are estimated from noisy speech online. Finally, following the synthesis principle of BCC cue parameters, the speech estimator is constructed for enhancing noisy speech. The test results demonstrate that, for the segmental signal-noise-ratio (SNR), the log spectral distortion and PESQ measures, the proposed method performs better than the reference methods.
引用
收藏
页数:4
相关论文
共 50 条
  • [41] HMM-Based Finnish Text-to-Speech System Utilizing Glottal Inverse Filtering
    Raitio, Tuomo
    Suni, Antti
    Pulakka, Hannu
    Vainio, Martti
    Alku, Paavo
    INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 1881 - +
  • [42] EVALUATION OF HMM-BASED LAUGHTER SYNTHESIS
    Urbain, Jerome
    Cakmak, Huseyin
    Dutoit, Thierry
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7835 - 7839
  • [43] Codebook-based Speech Enhancement with Bayesian LP Parameters Estimation
    Wang, Qing
    Bao, Chang-chun
    2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2015, : 1245 - 1248
  • [44] Speech enhancement denoising algorithm based on parameters estimation and perception improvement
    Wang J.
    Yin D.
    Jiang S.
    Yang L.
    Xie X.
    Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2016, 38 (01): : 174 - 179
  • [45] State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis
    Wu, Yi-Jian
    Nankaku, Yoshihiko
    Tokuda, Keiichi
    INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 516 - 519
  • [46] Minimum unit selection error training for HMM-based unit selection speech synthesis system
    Ling, Zhen-Hua
    Wang, Ren-Hua
    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 3949 - 3952
  • [47] Nonnegative HMM for Babble Noise Derived From Speech HMM: Application to Speech Enhancement
    Mohammadiha, Nasser
    Leijon, Arne
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2013, 21 (05): : 998 - 1011
  • [48] Minimum generation error criterion considering global/local variance for HMM-based speech synthesis
    Wu, Yi-Jian
    Zen, Heiga
    Nankaku, Yoshilliko
    Tokuda, Keiichi
    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4621 - 4624
  • [49] A NOVEL NMF-HMM SPEECH ENHANCEMENT ALGORITHM BASED ON POISSON MIXTURE MODEL
    Xiang, Yang
    Shi, Liming
    Hojvang, Jesper Lisby
    Rasmussen, Morten Hojfeldt
    Christensen, Mads Grasboll
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 721 - 725
  • [50] An NMF-HMM Speech Enhancement Method based on Kullback-Leibler Divergence
    Xiang, Yang
    Shi, Liming
    Hojvang, Jesper Lisby
    Rasmussen, Morten Hojfeldt
    Christensen, Mads Graesboll
    INTERSPEECH 2020, 2020, : 2667 - 2671