Automatic disordered sound repetition recognition in continuous speech using CWT and kohonen network

• Autorzy: Codello I. , Kuniszyk-Jóźkowiak W. , Smołka E. , Kobus A.

Identyfikatory

DOI

10.2478/v10065-012-0014-2

• Języki publikacji: EN

Abstrakty

EN

Automatic disorders recognition in speech can be very helpful for a therapist while monitoring therapy progress of patients with disordered speech. This article is focused on sound repetitions. The signal is analyzed using Continuous Wavelet Transform with 16 bark scales. Using the silence finding algorithm, only speech fragments are automatically found and cut. Each cut fragment is converted into a fixed-length vector and passed into the Kohonen network. Finally, the Kohonen winning neuron result is put on the 3-layer perceptron. Most of the analysis was performer and the results were obtained using the authors’ program WaveBlaster. We use the STATISTICA package for finding the best perceptron which was then imported back into WaveBlaster and used for automatic blockades finding. The problem presented in this article is a part of our research work aimed at creating an automatic disordered speech recognition system.

Słowa kluczowe

EN

speech recognition; speech disorders; sound repetition; Continuous Wavelet Transform; WaveBlaster

• Wydawca: Wydawnictwo UMCS
• Czasopismo: Annales Universitatis Mariae Curie-Skłodowska. Sectio AI, Informatica
• Rocznik: 2012
• Tom: Vol. 12, no. 2
• Strony: 39--48
• Opis fizyczny: Bibliogr. 20 poz., rys., tab.

Twórcy

autor

Codello I.

• Institute of Computer Science, Maria Curie-Skłodowska University pl. M. Curie-Skłodowskiej 1, 20-036 Lublin, Poland

autor

Kuniszyk-Jóźkowiak W.

• Institute of Computer Science, Maria Curie-Skłodowska University pl. M. Curie-Skłodowskiej 1, 20-036 Lublin, Poland

autor

Smołka E.

• Institute of Computer Science, Maria Curie-Skłodowska University pl. M. Curie-Skłodowskiej 1, 20-036 Lublin, Poland

autor

Kobus A.

• Institute of Computer Science, Maria Curie-Skłodowska University pl. M. Curie-Skłodowskiej 1, 20-036 Lublin, Poland

Bibliografia

• [1] Suszyński W., Kuniszyk–Jóźkowiak W., Smołka E., Dzieńkowski M., Automatic recognition of non-fluent stops, Annales UMCS Informatica (2004): 183.
• [2] Wiśniewski M., Kuniszyk–Jóźkowiak W., Smołka E., Suszyński W., Improved approach to automatic etection of speech disorders based on the Hidden Markov Models approach, Journal Of Medical Informatics & Technologies 15 (2010): 145.
• [3] Kobus A., Kuniszyk–Jóźkowiak W., Smołka E., Codello I., Speech nonfluency detection and classification based on linear prediction coefficients and neural networks, Journal Of Medical Informatics & Technologies 15 (2010): 135.
• [4] Szczurowska I., Kuniszyk–Jóźkowiak W., Smołka E., Speech nonfluency detection using Kohonen networks, Neural Computing and Application 18(7) (2009): 677.
• [5] Akansu A. N, Haddad R. A., Multiresolution signal decomposition, Academic Press (2001).
• [6] Codello I., Kuniszyk–JóźkowiakW.,Wavelet analysis of speech signal, Annales UMCS Informatica AI 6 (2007): 103.
• [7] Nayak J., Bhat P. S., Acharya R., Aithal U. V., Classification and analysis of speech abnormalities, Elsevier SAS 26(5-6) (2005): 319.
• [8] Gold B., Morgan N., Speech and audio signal processing, JOHN WILEY & SONS, INC (2000).
• [9] Smith J., Abel J, Bark and ERB Bilinear Transforms, IEEE Transactions on Speech and Audio Processing (1999).
• [10] Goupillaud P., Grossmann A., Morlet J., Cycle-octave and related transforms in seismic signal analysis’, Geoexploration 23 (1984–1985): 85.
• [11] Traunmüller H., Analytical expressions for the tonotopic sensory scale, J. Acoust. Soc. Am. 88 (1990): 97.
• [12] Codello I., Kuniszyk-JóźkowiakW., Smołka E., Kobus A., Prolongation Recognition in Disordered Speech, Valencia, Spain, Proceedings of International Conference on Fuzzy Computation (2010): 392.
• [13] Garfield S., Elshaw M., And Wermter S., Self-orgazizing networks for classification learning from normal and aphasic speech, In The 23rd Conference of the Cognitive Science Society, Edinburgh, Scotland (2001).
• [14] Horzyk A., Tadeusiewicz R., Self-optimizing neural networks, Advances in neural networks - ISNN 2004, pt 1, Lecture notes in computer science 3173 (2004): 150.
• [15] Horzyk A., Tadeusiewicz R., Mechanisms, symbols and models underlying cognition, pt 1, Proceedings, Lecture notes in Computer Science, 3561 (2005): 156.
• [16] Kohonen T., Self-Organizing Maps 34 (2001): 2173.
• [17] Tadeusiewicz R., Elementarne wprowadzenie do sieci neuronowych z przykładowymi programami, Akademicka Oficyna Wydawnicza, Warszawa (1998).
• [18] Tadeusiewicz R., Sieci neuronowe, Akademicka Oficyna Wydawnicza, Warszawa (1993).
• [19] Szczurowska I., Kuniszyk–Jóźkowiak W., Smołka E., Application of Artificial Neural Networks In Speech Nonfluency Recognition, Polish Jurnal of Environmental Studies 16(4A) (2007): 335.
• [20] Codello I., Kuniszyk–Jóźkowiak W., Smołka E., Kobus A., Disordered sound repetition recognition in continuous speech using CWT and Kohonen network, Journal Of Medical Informatics & Technologies 17 (2011): 123.