Browse > Article

Quantization Based Speaker Normalization for DHMM Speech Recognition System  

신옥근 (한국해양대학교 자동차정보공학부)
Abstract
There have been many studies on speaker normalization which aims to minimize the effects of speaker's vocal tract length on the recognition performance of the speaker independent speech recognition system. In this paper, we propose a simple vector quantizer based linear warping speaker normalization method based on the observation that the vector quantizer can be successfully used for speaker verification. For this purpose, we firstly generate an optimal codebook which will be used as the basis of the speaker normalization, and then the warping factor of the unknown speaker will be extracted by comparing the feature vectors and the codebook. Finally, the extracted warping factor is used to linearly warp the Mel scale filter bank adopted in the course of MFCC calculation. To test the performance of the proposed method, a series of recognition experiments are conducted on discrete HMM with thirteen mono-syllabic Korean number utterances. The results showed that about 29% of word error rate can be reduced, and that the proposed warping factor extraction method is useful due to its simplicity compared to other line search warping methods.
Keywords
Speech recognition; Speaker normalization; Warping; Vector quantization;
Citations & Related Records
연도 인용수 순위
  • Reference
1 /
[ J.E.Hamaker ] / MLLR: A speaker adaptation technique for LVCSR, Lecture note
2 An algorithm for vector quantizer design /
[ Y.Linde;A.Buzo;R.M.Gray ] / IEEE Transactions on Communications
3 Acoustic-Feature-based Frequency Warping For Speaker Normalization /
[ E.B.Gouvea ] / Thesis, Carneigie Mellon University
4 Vocal Tract Length Normalization for Large Vocabulary Continuous Speech Recognition /
[ P.Zhan;Alex Waibel ] / Language Technologies Institute Technical Report: CMU-LTI-97-150, Carnegie Melon University
5 A parametric approach to vocal tract length normalization /
[ E.Edie;H.Gish ] / ICASSP
6 A study on speaker adaptation of continuous density HMM parameters /
[ C.H.Lee;C.H.Lin;B.H.Juang ] / Proc. of the ICASSP
7 Recent advances in speaker recognition /
[ S.Furui ] / Pattern Recognition Letters   DOI   ScienceOn
8 Speaker normalization using constrained spectral shifts in auditory filter domain /
[ Y.Ono;H.Wakita;Y.Zhao ] / EuroSpeech
9 Comparison of clustering algorithms in speaker identification /
[ T.Kinnunen;T.Kilpelainen;P.Franti ] / SPC
10 A frequency warping approach to speaker normalization /
[ L.Lee;R.C.Rose ] / IEEE Trans. on Speech and Audio Processing   DOI   ScienceOn
11 Multiresolution channel normalization for ASR in reverberant environments /
[ C.Avendano;S.Tibrewala;H.Hermansky ] / EUROSPEECH
12 A study on speaker normalization using vocal tract normalization and speaker adaptive training /
[ L.Welling;R.Haeb-Umbach;X.Aubert;N.Haberland ] / ICASSP98
13 Speaker verification with vector quantisation /
[ P.G.Pop;E.Lupu ] / Proc. Trends and Recent Achievements in Information Technology
14 Maximum likelihood linear regression for speaker adaptation of continuos density hidden markov models /
[ C.Leggetter;P.Woodland ] / Computer Speech and Language   DOI   ScienceOn