ViVoVAD: a Voice Activity Detection Tool based on Recurrent Neural Networks

Authors

  • Pablo Gimeno Jordán University of Zaragoza image/svg+xml
  • Ignacio Viñals Bailo ,
  • Alfonso Ortega Giménez ,
  • Antonio Miguel Artiaga ,
  • Eduardo Lleida Solano ,

DOI:

https://doi.org/10.26754/jji-i3a.003524

Abstract

Voice Activity Detection (VAD) aims to distinguish
correctly those audio segments containing human
speech. In this paper we present our latest approach
to the VAD task that relies on the modelling
capabilities of Bidirectional Long Short Term
Memory (BLSTM) layers to classify every frame in
an audio signal as speech or non-speech

Downloads

Download data is not yet available.

Downloads

Published

2019-05-20

Issue

Vol. 7: Actas de la VIII Jornada de Jóvenes Investigadores del I3A - 6 de junio de 2019

Section

Artículos (Tecnologías de la Información y las Comunicaciones)

How to Cite

Gimeno Jordán, P., Bailo, I. V., Giménez, A. O., Artiaga, A. M., & Solano, E. L. (2019). ViVoVAD: a Voice Activity Detection Tool based on Recurrent Neural Networks. Jornada De Jóvenes Investigadores Del I3A, 7. https://doi.org/10.26754/jji-i3a.003524