Automatic detection and classification of phoneme repetitions using HTK toolkit

• Autorzy: Wiśniewski M. , Kuniszyk-Jóźkowiak W.
• Języki publikacji: EN

Abstrakty

EN

The therapy of stuttering people is based on a proper selection of texts and then on a practice of their articulation by reading or narration. The texts are chosen on the basis of kind and intensity of dysfluencies appearing in a speech. Thus there is still a requirement to find effective and objective methods of analysis of dysfluent speech. Hidden Markov models are stochastic models widely used in recognition of any patterns appearing in a signal. In the work a simple monophone system based on the Hidden Markov Model Toolkit was built and tested in the context of detection and classification of phoneme repetitions - a common speech disorder in the Polish language.

Słowa kluczowe

EN

HMM; recognition; speech; disorders

PL

rozpoznanie; mowa; zaburzenia

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2011
• Tom: Vol. 17
• Strony: 141--147
• Opis fizyczny: Bibliogr. 13 poz., rys., tab.

Twórcy

autor

Wiśniewski M.

autor

Kuniszyk-Jóźkowiak W.

Bibliografia

• [1] ACHIBALD L., DE NIL L.F., The relationship between stuttering severity and kinesthetic acuity for jaw movements in adults who stutter, Journal of Fluency Disorders, Vol. 24(1), Elsvier, 1999, pp. 25-42.
• [2] CZYŻEWSKI A., KACZMAREK A., KOSTEK B., Intelligent processing of stuttered speech, Journal of Intelligent Information Systems, Vol. 21(2), Kluwer Academic Publishers, The Nederlands, 2003, pp. 143-171.
• [3] GAJECKI L., TADEUSIEWICZ R., Modeling of Polish Language for Large Vocabulary Computer Speech Recognition, Speech and Language Technology, Vol. 11, Poznań, 2008, pp. 65-70.
• [4] HORNE R. S., Spectrogram for Windows, ver. 3.2.1.
• [5] HOWELL P., SACKIN S., Automatic recognition of repetitions and prolongations in stuttered speech, Proceedings of the First World Congress on Fluency Disorders, 1995, pp. 372-374.
• [6] http://htk.eng.cam.ac.uk/docs/docs.shtml.
• [7] JASSEM W, Podstawy fontetyki akustycznej, PWN, Warszawa, 1973, (in Polish).
• [8] SMOŁKA E., KUNISZYK-JÓŹKOWIAK W., SUSZYŃSKI W., DZIEŃKOWSKI M., SZCZUROWSKA I., Speech Nonfluecy Recognition in Two Stages of Kohonen Networks, Structures-Waves-Human Health, Zakopane, 2004, pp. 139-142.
• [9] SZCZUROWSKA I., KUNISZYK-JÓŹKOWIKAK W., SMOŁKA E., The Application of Kohonen and Multilayer Perceptron Networks in the Speech Nonfluecy Analysis, Archives of Acoustics, Vol. 31, 2006, pp. 205.
• [10] TADEUSIEWICZ R., Speech Recognition with Application of Neural Networks, Seminar of Polish Phonetical Society, Warszawa, 1994, pp. 137-150.
• [11] WIŚNIEWSKI M., KUNISZYK-JÓŹKOWIAK W., SMOŁKA E., SUSZYŃSKI W., Automatic detection of disorders in a continuous speech with the Hidden Markov Models approach, Advances in Soft Computing 45, Computer Recognition Systems 2, Vol. 45, Springer-Verlag, Berlin Heildelberg, 2008, pp. 445-453.
• [12] WIŚNIEWSKI M., KUNISZYK-JÓŹKOWIAK W., SMOŁKA E., SUSZYŃSKI W., Improved approach to automatic detection of speech disorders based on the Hidden Markov Models approach, Journal of Medical Informatics and Technologies, Vol.15, Computer Systems Dep., University od Silesia, Poland, 2010, pp. 145-152.
• [13] WSZOŁEK W., TADEUSIEWICZ R. The Evaluation of Effectiveness of Various Neural Network Types in Pathological Speech Analysis, XLVII Open Seminar on Acoustics OSA`2000, Vol. 2, Rzeszów – Jawor, 2000, pp. 721-728.