Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Language and noise transfer in speech enhancement generative adversarial network

Autor
Pascual, S.; Park, M.; Serra, J.; Bonafonte, A.; Ahn, K.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
2018 IEEE International Conference on Acoustics, Speech, and Signal Processing
Any de l'edició
2018
Data de presentació
2018-04-15
Llibre d'actes
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): proceedings
Pàgina inicial
5019
Pàgina final
5023
DOI
https://doi.org/10.1109/ICASSP.2018.8462322 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/122808 Obrir en finestra nova
URL
https://ieeexplore.ieee.org/document/8462322 Obrir en finestra nova
Resum
Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those systems into new, low resource environments an important topic. In this work, we present the results of adapting a speech enhancement generative adversarial network by fine-tuning the generator with small amounts of data. We investigate the minimum requirements to obtain a stable behavior in terms of several objective me...
Paraules clau
Deep learning, Generative adversarial networks, Speech enhancement, Transfer learning
Grup de recerca
IDEAI-UPC Intelligent Data Science and Artificial Intelligence
TALP - Centre de Tecnologies i Aplicacions del Llenguatge i la Parla
VEU - Grup de Tractament de la Parla

Participants