Публікація: Analysis of the influence of selected audio pre-processing stages on accuracy of speaker language recognition
Завантаження...
Дата
2023
Назва журналу
ISSN журналу
Назва тома
Видавництво
ХНУРЕ
Анотація
In the course of the work, the best sequence of stages of pre-processing audio data was selected for use in further training of the neural network for different ways to convert signals into features. Mel-cepstral characteristic coefficients are better suited for solving our problem. Since the neural network strongly depends on its structure, the results may change with the increase in the volume of input data and the number of languages. But at this stage, it was decided to use only mel-cepstral characteristic coefficients with normalization.
Опис
Ключові слова
mel-cepstral characteristic coefficients, spectrogram, time mask, frequency mask, neural network, voice, audio series
Бібліографічний опис
Barkovska O. Yu. Analysis of the influence of selected audio pre-processing stages on accuracy of speaker language recognition / O. Yu. Barkovska, A. O. Havrashenko // Сучасний стан наукових досліджень та технологій в промисловості. – 2023. – № 4(26). – С. 16–23. – DOI: https://doi.org/10.30837/ITSSI.2023.26.016.