@inproceedings{74e7f40d31414473a0b49f4526c18147,
title = "Joint Phoneme Alignment and Text-Informed Speech Separation on Highly Corrupted Speech",
abstract = "Speech separation quality can be improved by exploiting textual information. However, this usually requires text-to-speech alignment at phoneme level. Classical alignment methods are made for rather clean speech and do not work as well on corrupted speech. We propose to perform text-informed speech-music separation and phoneme alignment jointly using recurrent neural networks and the attention mechanism. We show that it leads to benefits for both tasks. In experiments, phoneme transcripts are used to improve the perceived quality of separated speech over a non-informed baseline. Moreover, our novel phoneme alignment method based on the attention mechanism achieves state-of-the-art alignment accuracy on clean and on heavily corrupted speech.",
keywords = "Speech separation, attention, informed source separation, phoneme alignment",
author = "Kilian Schulze-Forster and Doire, \{Clement S.J.\} and Gael Richard and Roland Badeau",
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/ICASSP40776.2020.9053182",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "7274--7278",
booktitle = "2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings",
}