DeepVoice: Tecnologías de Aprendizaje Profundo aplicadas al Procesado de Voz y Audio.

Marta R. Costa-jussà José A. R. Fonollosa

Published in: Proces. del Leng. Natural (2017)

Keyphrases

multimedia
visual information
audio visual
music genre classification
feature extraction
cross modal
broadcast news
real world
audio recordings
audio video
signal processing
visual data
audio signals
audio stream
video recordings
audio signal
case study
feature selection
computer vision
genetic algorithm