Optimal acoustic model complexity selection in polish medical speech recognition

• Autorzy: Sas J. , Poreba T.
• Języki publikacji: EN

Abstrakty

EN

In the paper, the method of acoustic model complexity level selection for automatic speech recognition is proposed. Selection of the appropriate model complexity affects significantly the accuracy of speech recognition. For this reason the selection of the appropriate complexity level is crucial for practical speech recognition applications, where end user effort related to the implementation of speech recognition system is important. We investigated the correlation between speech recognition accuracy and two popular information criteria used in statistical model evaluation: Bayesian Information Criterion and Akaike Information Criterion computed for applied acoustic models. Experiments carried out for language models related to general medicine texts and radiology diagnostic reporting in CT and MR showed strong correlation of speech recognition accuracy and BIC criterion. Using this dependency, the procedure of Gaussian mixture count selection for acoustic model was proposed. Application of this procedure makes it possible to create the acoustic model maximizing the speech recognition accuracy without additional computational costs related to alternative cross-validation approach and without reduction of training set size, which is unavoidable in the case of cross-validation approach.

Słowa kluczowe

EN

speech recognition; language models; medical information systems

PL

rozpoznawanie mowy; modele języka; medyczne systemy informacji

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2011
• Tom: Vol. 17
• Strony: 115--122
• Opis fizyczny: Bibliogr. 15 poz., rys.

Twórcy

autor

Sas J.

• Instutute of Informatics, Wroclaw University of Technology, 50-370 Wroclaw, ul. Wyb. Wyspianskiego 27, Poland

autor

Poreba T.

Bibliografia

• [1] HAO Y., Speech-Recognition Technology in Health Care and Special-Needs Assistance, IEEE Signal Processing Magazine, Vol. 87, 2009.
• [2] KOIVIKKO M.P., KAUPINNEN T, AHOVUO J., Improvement of report workflow and productivity using speech recognition - a follow-up study, Journal of Digital Imaging, Vol. 21, No 4, 2008, pp. 378-382.
• [3] LANGER S.G., Impact of Speech Recognition on Radiologist Productivity, Journal of Digital Imaging, Vol. 15, No 4, 2002, pp. 203-209.
• [4] PEZZULLO J.A., TUNG G.A., ROGG J.M., DAVIS L.M., BRODY J.M., MAYO_SMITH W.W., Voice recognition dictation: radiologist as transcriptionist. Journal of Digital Imaging, Vol. 21, No 4, 2008, pp. 384-389.
• [5] HNATKOWSKA B., SAS J., Application of Automatic Speech Recognition to Medical Reports Spoken in Polish, Journal of Medical Informatics & Technologies, Vol 12, 2008, pp. 223-230.
• [6] JELINEK F., Statistical Methods for Speech Recognition, MIT Press, Cambridge, Massachusetts, 1997.
• [7] JURAFSKY D., MARTIN J., Speech and Language Processing. An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition, Prentice Hall, New Jersey, 2000.
• [8] LEE A., KAWAHARA T., SHIKANO K., Julius - an Open Source Real-Time Large Vocabulary Recognition Engine, Proc. of European Conference on Speech Communication and Technology (EUROSPEECH), 2001, pp. 1691-1694.
• [9] YOUNG S., EVERMAN G., The HTK Book (for HTK Version 3.4), Cambridge University Engineering Department, 2009.
• [10] SCHWARZ G., Estimating the Dimension of a Model, The Annals of Statistics, Vol. 6., No. 2, 1978, pp. 461-464.
• [11] LIDDLE A.R., Information Criteria for Astrophysical Model Selection, Monthly Notices of the Royal Astronomical Society: Letters, Vol. 377, No 1, 2007, pp. 74-78.
• [12] EVANS J., SULLIVAN J., Approximating Model Probabilities in Bayesian Information Criterion and Decision-Theoretic Approaches to Model Selection in Phylogenetics, Mol. Biol. Evol. Vol. 28, No 1, 2011, pp. 343–349.
• [13] ACQUAH H., Comparison of Akaike information criterion (AIC) and Bayesian information criterion (BIC) in selection of an asymmetric price relationship, Journal of Development and Agricultural Economics Vol. 2(1), 2010, pp. 001-006.
• [14] AKAIKE H., A new look at the statistical model identification, IEEE Trans. on Automatic Control, , Vol 19, No 6, 1974, pp. 716-723.
• [15] BURNHAM K. P., ANDERSON D. R., Multimodel inference: Understanding AIC and BIC in model selection, Sociological Methods and Research, Vol 33, No 2, 2004, pp. 261-304.