A PITCH BASED NOISE ESTIMATION TECHNIQUE FOR ROBUST SPEECH RECOGNITION WITH MISSING DATA

被引：0
|
作者：
Morales-Cordovilla, Juan A. [1 ]
Ma, Ning [2 ]
Sanchez, Victoria [1 ]
Carmona, Jose L. [1 ]
Peinado, Antonio M. [1 ]
Barker, Jon [2 ]
机构：
[1] Univ Granada, Dept Teoria Senal Telemat & Comunicac, E-18071 Granada, Spain
[2] Univ Sheffield, Dept Comp Sci, Sheffield, South Yorkshire, England
来源：
2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2011年
基金：
英国工程与自然科学研究理事会;
关键词：
Robust speech recognition; missing data; noise estimation; VAD; harmonic tunnelling;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This paper presents a noise estimation technique based on knowledge of pitch information for robust speech recognition. In the first stage the noise is estimated by means of extrapolating the noise from frames where speech is believed to be absent. These frames are detected with a proposed pitch based VAD (Voice Activity Detector). In the second stage the noise estimation is revised in voiced frames using harmonic tunnelling thechnique. The tunnelling noise estimation is used at high SNRs as an upper bound of the noise rather than a suitable estimation. A spectrogram MD (Missing Data) recognition system is chosen to evaluate the proposed noise estimation. The proposed system is compared in Aurora-2 with other similar techniques like cepstral SS (Spectral Subtraction).
引用
收藏
页码：4808 / 4811
页数：4
相关论文
共 50 条
  • [31] HMM-Based Estimation of Unreliable Spectral Components for Noise Robust Speech Recognition
    Borgstroem, Bengt J.
    Alwan, Abeer
    INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 1769 - 1772
  • [32] Noise suppression based on wavelet packet decomposition and quantile noise estimation for robust automatic speech recognition
    Rank, Erhard
    Van Pham, Tuan
    Kubin, Gernot
    2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Vols 1-13, 2006, : 477 - 480
  • [33] Vector-Quantization based Mask Estimation for Missing Data Automatic Speech Recognition
    Van Segbroeck, Maarten
    Van Hamme, Hugo
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1825 - 1828
  • [34] Zero-crossing based binaural mask estimation for missing data speech recognition
    Kim, Young-Ik
    An, Sung Jun
    Kil, Rhee Man
    2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Vols 1-13, 2006, : 4947 - 4950
  • [35] A robust pitch estimation algorithm in noise
    Shahnaz, C.
    Zhu, W. -P.
    Ahmad, M. O.
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 1073 - +
  • [36] Robust Recognition of Noisy Speech Through Partial Imputation of Missing Data
    Kian Ebrahim Kafoori
    Seyed Mohammad Ahadi
    Circuits, Systems, and Signal Processing, 2018, 37 : 1625 - 1648
  • [37] Robust Recognition of Noisy Speech Through Partial Imputation of Missing Data
    Kafoori, Kian Ebrahim
    Ahadi, Seyed Mohammad
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2018, 37 (04) : 1625 - 1648
  • [38] Multi-candidate missing data imputation for robust speech recognition
    Yujun Wang
    Hugo Van hamme
    EURASIP Journal on Audio, Speech, and Music Processing, 2012
  • [39] Multi-candidate missing data imputation for robust speech recognition
    Wang, Yujun
    Van Hamme, Hugo
    EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2012,
  • [40] On noise masking for automatic missing data speech recognition: A survey and discussion
    Cerisara, Christophe
    Demange, Sebastien
    Haton, Jean-Paul
    COMPUTER SPEECH AND LANGUAGE, 2007, 21 (03): : 443 - 457
12345