Browse > Article

Channel-attentive MFCC for Improved Recognition of Partially Corrupted Speech  

조훈영 (한국과학기술원 전자전산학과 전산학전공)
지상문 (경성대학교 컴퓨터과학과)
오영환 (한국과학기술원 전자전산학과 전산학전공)
Publication Information
The Journal of the Acoustical Society of Korea / v.22, no.4, 2003 , pp. 315-322 More about this Journal
Abstract
We propose a channel-attentive Mel frequency cepstral coefficient (CAMFCC) extraction method to improve the recognition performance of speech that is partially corrupted in the frequency domain. This method introduces weighting terms both at the filter bank analysis step and at the output probability calculation of decoding step. The weights are obtained for each frequency channel of filter bank such that the more reliable channel is emphasized by a higher weight value. Experimental results on TIDIGITS database corrupted by various frequency-selective noises indicated that the proposed CAMFCC method utilizes the uncorrupted speech information well, improving the recognition performance by 11.2% on average in comparison to a multi-band speech recognition system.
Keywords
Partially corrupted speech; Frequency-selective noise; Multi-band speech recognition; Channel-attentive MFCC;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Robust automatic speech recognition with missing and unreliable acoustic data /
[ M.Cook;P.Green;L.Josifovski;A.Vizinho ] / Speech Communication   DOI   ScienceOn
2 다중대역 음성인식을 위한 부대역 신뢰도의 추정 및 가중 /
[ 조훈영;지상문;오영환 ] / 한국음향학회지   과학기술학회마을
3 Adaptive ML-weighting in multi-band recombination of gaussian mixture ASR /
[ A.Hagen;H.Bourlard;A.Morris ] / Proc. of International Conference on Acoustics, Speech and Signal Processing
4 Multi-Stream adaptive evidence combination for noise robust ASR /
[ A.Morris;A.Hagen;H.Glotin;H.Bourlard ] / Speech Communication   DOI   ScienceOn
5 Towards ASR on partially corrupted speech /
[ H.Hermansky;S.Tibrewala;M.Pavel ] / Proc. of International Conference on Spoken Language Processing
6 Suppression of acoustic noise in speech using spectral subtraction /
[ S.Boll ] / IEEE Trans. On Speech and Audio Processing   DOI
7 How do humans process and recognize speech /
[ J.B.Allen ] / IEEE Trans. On Speech and Audio Processing   DOI   ScienceOn
8 A recombination strategy for multi-band speech recognition based on mutual information criterion /
[ S.Okawa;T.Nakajima;K.Shiral ] / Proc. of European Conference on Speech Communication and Technology
9 Robust continuous speech recognition using parallel model combination /
[ M.J.F.Gales;S.J.Young ] / IEEE Trans. On Speech and Audio Processing   DOI   ScienceOn
10 Robust Speech Recognition based on Partial Information Technique /
[ H.Y.Cho ] / Ph.D. Dissertation, Department of Electrical Engineering and Computer Science, Division of Computer Sciecnce, KAIST
11 The full combination sub-bands approach to noise robust HMM/ANN based ASR /
[ A.Morris;A.Hagen;H.Bourlard ] / Proc. of European Conference on Speech Communication and Technology
12 Robust speech recognition using probabilistic union models /
[ J.Ming;P.Jancovic;F.J.Smith ] / IEEE Trans. On Speech and Audio Processing   DOI   ScienceOn
13 Multi-band speech recognition in noisy environments /
[ S.Okawa;E.Bocchieri;A.Potamianos ] / Proc. of International Conference on Acoustics, Speech and Signal Processing