- Full text PDF available (9)
- This year (0)
- Last 5 years (0)
- Last 10 years (1)
Journals and Conferences
The nonlinear speech signal decomposition based on Volterra-Wiener functional series is described. The nonlinear filter bank structure is proposed for phonemes recognition solving.
The nonlinear speech signal decomposition based on Volterra-Wiener functional series is described. The solution of phoneme recognition problem by means of measuring Wiener kernels is proposed.
The speech-based analysis of speaker individual features has found wide application area. In order to analyse the speaker individual features it is necessary to use high frequencies and accurate spectrum estimation methods. It was found out that the best way to analyse the personal voice individuality is to use bark scaled spectrum estimation based on… (More)
The nonlinear speech signal decomposition based on Volterra-Wiener functional series is described. The solution of speech recognition problem by means of measuring Wiener kernels is proposed. The recognition system of speech signal is considered for speech phoneme identification.
The approach to the problem of voice variability solving based on nonlinear VolterraWiener filtering is proposed.
This paper presents the nonlinear speech phoneme decomposition based on Volterra-Wiener functional series. It is shown the usage this nonlinear decomposition in speech recognition systems constructing. The fast algorithms for finding estimation of Wiener kernels in frequency domain permit to reduce essentially computing expenses for evaluation of signals… (More)
Alexander M. Krot, Mikhail A. Shcherbakov and Polina P. Tkachova Institute of Engineering Cybernetics of the National Academy of Sciences of Belarus Surganov Str., 6, 220012, Minsk, Belarus e-mail: email@example.com Tel.: (375) 172 842086, Fax.: (375) 172 318403 State Technical University of Penza Krasnaya Str., 40, 440017, Penza, Russia… (More)
The recognition and training algorithms for autoregressive hidden Markov models were developed in order to solve the task of vocal fold pathology detection. Three databases were created and used for 3 vocal pathologies detection. During the experiments the proposed vocal tract pathology detection system based on autoregressive hidden Markov models and… (More)
This paper investigates the approach for revealing pathological speech signal based on estimating specific geometric structure of Lorenz attractor in a chaotic regime. Analysis of the Lorenz attractor on the basis of proposed nonlinear decomposition into matrix series is developed. This analysis permits to estimate the values of characteristic parameters… (More)