Speech activity detection for the automated speaker recognition system of critical use
| Autor: | O. O. Maksimov, V. V. Kovtun, M. M. Bykov |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
wavelet transformation
convolution neural network automated speaker recognition system of critical use Voice activity detection Computer Science::Sound lcsh:TA1-2040 Computer science Speech recognition speech activity detection Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) lcsh:Engineering (General). Civil engineering (General) Speaker recognition system |
| Zdroj: | Журнал інженерних наук, Vol 4, Iss 1, Pp H14-H20 (2017) |
| ISSN: | 2414-9381 2312-2498 |
| Popis: | In the article, the authors developed a method for detecting speech activity for an automated system for recognizing critical use of speeches with wavelet parameterization of speech signal and classification at intervals of “language”/“pause” using a curvilinear neural network. The method of wavelet-parametrization proposed by the authors allows choosing the optimal parameters of wavelet transformation in accordance with the user-specified error of presentation of speech signal. Also, the method allows estimating the loss of information depending on the selected parameters of continuous wavelet transformation (NPP), which allowed to reduce the number of scalable coefficients of the LVP of the speech signal in order of magnitude with the allowable degree of distortion of the local spectrum of the LVP. An algorithm for detecting speech activity with a curvilinear neural network classifier is also proposed, which shows the high quality of segmentation of speech signals at intervals "language" / "pause" and is resistant to the presence in the speech signal of narrowband noise and technogenic noise due to the inherent properties of the curvilinear neural network. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|