@inproceedings{f7c6cd98060d4292b8b07a9c2251e06a,
title = "Neutral to Lombard Speech Conversion with Deep Learning",
abstract = "In this paper, we propose several approaches for neutral to Lombard speech conversion. We study in particular the influence of different recurrent neural network architectures where their main hyper-parameters are carefully selected using a bandit-based approach. We also apply the Continuous Wavelet Transform (CWT) as a multi-resolution analysis framework to better model temporal dependencies of the different features selected. The speech conversion results obtained are validated by means of objective evaluations which highlight in particular the interest of the wavelet transform for the learning process.",
keywords = "deep learning, lombard effect, recurrent neural networks, speaking style conversion, wavelets",
author = "Enguerrand Gentet and Bertrand David and Sebastien Denjean and Gael Richard and Vincent Roussarie",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 ; Conference date: 04-05-2020 Through 08-05-2020",
year = "2020",
month = may,
day = "1",
doi = "10.1109/ICASSP40776.2020.9053006",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "7739--7743",
booktitle = "2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings",
}