Электронный каталог

34
M23
Mamyrbayev, O.
    Modern trends in development of speech recognition systems [Текст] / O. Mamyrbayev, D. Oralbekova // News of the National Academy of sciences of the Republic of Kazakhstan. - 2020. - №4. - P. 42-51
ББК 34

Рубрики: Technics

Кл.слова (ненормированные):
automatic speech recognition -- hidden markov models -- end-to-end -- neural networks -- ctc
Аннотация: This article presents the main ideas, advantages and disadvantages of models based on hidden Markov models - a Gaussian mixture models, end-to-end models and indicates that the end-to-end model is a developing area in the filed of speech recognition.
Держатели документа:
WKU
Доп.точки доступа:
Oralbekova, D.

32.973
M23
Mamyrbayev, O. Zh.
    Realization of online systems for automatic speech recognition. [Текст] / O. Zh. Mamyrbayev, D. O. Oralbekova, K. Alimhan, M. Othman, B. Zhumazhanov // News of national academy of sciences of the republic of Kazakhstan. - 2021. - №6. - P. 66-72
ББК 32.973

Рубрики: information Technology

Кл.слова (ненормированные):
automatic speech recognition -- monotonic chunkwise attention -- neural transducer -- RNN-T -- end-to-end
Аннотация: This article provides a detailed overview of popular online-based models for E2Esystems such as RNN-T, Neural Transducer (NT), Monotonic Chunkwise Attention (MoChA). Systems based on these models have been trained to recognize Kazakh speech. The results obtained showed that all three models work well for recognizing Kazakh speech without the use of external additions
Держатели документа:
WKU
Доп.точки доступа:
Oralbekova, D.O.
Alimhan, K.
Othman, M.
Zhumazhanov, B.