Project Details
Speech enhancement front-end for robust automatic speech recognition with large amount of training data
Project Period: 1. 1. 2021 – 31. 12. 2021
Project Type: contract
Partner: NTT Corporation
Czech title
Parametrizace s obohacováním řeči pro robustní automatické rozpoznávání řeči s velkým objemem trénovacích dat
Type
contract
Keywords
speech recognition, robustness, large data, DNN embeddings
Abstract
The purpose of the Joint Research is to develop Speech enhancement front-end for robust automatic speech recognition with large amount of training data through the cooperation of NTT and BUT. The work is relying on embeddings produced by neural networks in various places of the processing chain.
Team members
Žmolíková Kateřina, Ing., Ph.D.
(FIT)
– research leader
Černocký Jan, prof. Dr. Ing. (DCGM)
Kocour Martin, Ing. (DCGM)
Švec Ján, Ing. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
Kocour Martin, Ing. (DCGM)
Švec Ján, Ing. (DCGM)
Publications
2021
- DELCROIX, M.; ŽMOLÍKOVÁ, K.; OCHIAI, T.; KINOSHITA, K.; NAKATANI, T. Speaker activity driven neural speech extraction. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Toronto: IEEE Signal Processing Society, 2021.
p. 6099-6103. ISBN: 978-1-7281-7605-5. Detail