Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset

Abstract Audio signals represent a wide diversity of acoustic events, from background environmental noise to spoken communication. Machine learning models such as neural networks have already been proposed for audio signal modeling, where recurrent structures can take advantage of temporal dependenc...

Полное описание

Сохранить в:
Библиографические подробности
Главные авторы: Diego de Benito-Gorron, Alicia Lozano-Diez, Doroteo T. Toledano, Joaquin Gonzalez-Rodriguez
Формат: Artigo
Язык:Inglês
Опубликовано: SpringerOpen 2019-06-01
Серии:EURASIP Journal on Audio, Speech, and Music Processing
Предметы:
Acoustic event detection
Speech activity detection
Music activity detection
Neural networks
Convolutional networks
LSTM
Online-ссылка:http://link.springer.com/article/10.1186/s13636-019-0152-1
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!

Схожие документы