Browse > Article

ImprovementofMLLRAlgorithmforRapidSpeakerAdaptationandReductionofComputation  

Kim, Ji-Un (인하대학교 전자공학과 DSP Lab.)
Chung, Jae-Ho (인하대학교 전자공학과 DSP Lab.)
Publication Information
The Journal of Korean Institute of Communications and Information Sciences / v.29, no.1C, 2004 , pp. 65-71 More about this Journal
Abstract
We improved the MLLR speaker adaptation algorithm with reduction of the order of HMM parameters using PCA(Principle Component Analysis) or ICA(Independent Component Analysis). To find a smaller set of variables with less redundancy, we adapt PCA(principal component analysis) and ICA(independent component analysis) that would give as good a representation as possible, minimize the correlations between data elements, and remove the axis with less covariance or higher-order statistical independencies. Ordinary MLLR algorithm needs more than 30 seconds adaptation data to represent higher word recognition rate of SD(Speaker Dependent) models than of SI(Speaker Independent) models, whereas proposed algorithm needs just more than 10 seconds adaptation data. 10 components for ICA and PCA represent similar performance with 36 components for ordinary MLLR framework. So, compared with ordinary MLLR algorithm, the amount of total computation requested in speaker adaptation is reduced by about 1/167 in proposed MLLR algorithm.
Keywords
Speaker adaptation; MLLR; PCA; ICA;
Citations & Related Records
연도 인용수 순위
  • Reference
1 M.J.F. Gales, 'The Generation and Useof Regression Class Trees For MLLRAdaptation,'TR263, Cambridge Univ.,August, 1996
2 V. Digalakis. 'On-line adaptaion ofhidden Markov models using incrementalestimation algorithms.' Proc. 5th Eur.Conf. Speech Communication andTechnology. Sept. 1997, vol. 4. pp.1859-1862
3 Qiang Huo, and Bin Ma, 'OnlineAdaptive Learning of Continuous-Density Hidden Markov Models Basedon Multiple-Stream Prior Evolutionand Posterior Pooling,'IEEE Trans. OnSpeech and Audio Processing, Vol. 9,No. 4, May 2001, pp388-398   DOI   ScienceOn
4 M. E. Tipping. and C. M. Bishop,'Probabilistic Principal Component Analysis.' Journal of the RoyalStatistical Society. Serios B. 61, Part3, pp 611-612,1999   DOI   ScienceOn
5 J. T. Chien, 'Online hierarchicaltransformation of hidden Markovmodels for speech recognition,' IEEETrans. on Speech and Audio Processing.vo1.7 No. 6, Nov. 1999, pp 656-667   DOI   ScienceOn
6 C. J. Leggetter. Improved acousticmodelling for HMMs using lineartransforms, PhD Thesis, Univ. ofCambridge Feg. 1995
7 Aapo Hyvarinen, Juha Karhunen andErkki Oja, Independent ComponentAnalysis. Wi11y-Interscience,2001
8 A. Sankar and C. H. Lee. 'Amaximum-likelihood approach tostochastic matching for robust speechrecognition,' IEEE Trans. on SpeechAudio Processing. vol. 4. pp. 190-202 1996   DOI   ScienceOn
9 D. Ridder, J. Kittler, and R. P. W.Duin, 'Probabilistic PCS and ICAsubspace mixture models for imagesegmentation.' The Eleventh BritishMachine Vision Conference, ,pp.112-121,September, 2000
10 C. H. Lee, C. H. Lin, and B. H. Juang,'A study on speaker adaptation of theparameters of continuous densityhidden Markov models,' IEEE Transon Signal Processing, vol. 39, No. 4April 1991. pp 806-814   DOI   ScienceOn
11 O. Siohan, C. Chesta. and C. H. Lee'Joint maximum a posteriori adaptationof transformation and HMMparameters,' IEEE Trans. on Speechand Audio Processing, vol. 9, No. 4May 2001, pp 417-428   DOI   ScienceOn