|
Information Technologies and Telecommunications
Overview of current open solutions in the field of speech recognition
K. V. Nalchadzhi Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences,
360010, Russia, Nalchik, 2 Balkarov street
Abstract:
The purpose of this work is to review the most successful open solutions in the field of speech
recognition and also considers the processes of speech recognition and the possibilities of their practical
use. The paper presents classical solutions based on recurrent neural networks, as well as more modern
ones, which use convolutional neural networks as a basis to remove noise and reduce dimensionality, and
transformers that allow to memorize the context and work with the semantic meaning of sequences,
regardless of time.
Keywords:
artificial intelligence, speech recognition, neural networks, natural language processing,
convolutional neural networks, recurrent neural networks, transformers.
Received: 07.12.2022 Revised: 09.12.2022 Accepted: 13.12.2022
Citation:
K. V. Nalchadzhi, “Overview of current open solutions in the field of speech recognition”, News of the Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences, 2022, no. 6, 127–133
Linking options:
https://www.mathnet.ru/eng/izkab520 https://www.mathnet.ru/eng/izkab/y2022/i6/p127
|
Statistics & downloads: |
Abstract page: | 58 | Full-text PDF : | 36 | References: | 11 |
|