Реєстраційний номер
2124U014669, Матеріали видань та локальних репозитаріїв
Категорія
Стаття
Назва роботи
Neurorecognition visualization in multitask end-to-end speech
Автор
Mamyrbayev Orken
Pavlov Sergii
Bekarystankyzy Akbayan
Oralbekova Dina
Zhumazhanov Bagashar
Azarova Larysa
Mussayeva Dinara
Koval Tetiana
Gromaszek Konrad
Issimov Nurdaulet
Shiyapov Kadrzhan
Павлов С. В.
Азарова Л. Є.
Дата публікації
11-04-2024
Постачальник інформації
Вінницький національний технічний університет
Першоджерело
http://ir.lib.vntu.edu.ua/handle/123456789/41441
Видання
Society of Photo-Optical Instrumentation Engineers
Опис
Nowadays, speech-processing technologies with different language systems are successfully used in mobile and stationary devices. Kazakh is considered a low-resource language, which poses various challenges for conventional speech recognition methods. This paper presents a proposed model capable of multitasking and handling concurrent speech recognition, dialect identification, and speaker identification, all in an end-to-end framework. The developed multitask model enables training three different tasks within a single model. A multitask recognition system is created based on the WaveNet-CTC model. Experiments show that for the concrete task end-to-end multitask model has better performance than other models..
Додано/оновлено в НРАТ
2026-10-26
