Open Access Te Herenga Waka-Victoria University of Wellington
Browse

Handling Background Noise in Neural Speech Generation

Download (217.06 kB)
conference contribution
posted on 2021-06-28, 07:41 authored by Tom Denton, Alejandro Luebs, Michael Chinen, Felicia SC Lim, Andrew Storus, Hengchin Yeh, Willem KleijnWillem Kleijn, Jan Skoglund
Recent advances in neural-network based generative modeling of speech has shown great potential for speech coding. However, the performance of such models drops when the input is not clean speech, e.g., in the presence of background noise, preventing its use in practical applications. In this paper we examine the reason and discuss methods to overcome this issue. Placing a denoising preprocessing stage when extracting features and target clean speech during training is shown to be the best performing strategy.

History

Preferred citation

Denton, T., Luebs, A., Chinen, M., Lim, F. S. C., Storus, A., Yeh, H., Kleijn, W. B. & Skoglund, J. (2020, November). Handling Background Noise in Neural Speech Generation. In 2020 54th Asilomar Conference on Signals, Systems, and Computers 2020 54th Asilomar Conference on Signals, Systems, and Computers (00 pp. 667-671). IEEE. https://doi.org/10.1109/ieeeconf51394.2020.9443535

Conference name

2020 54th Asilomar Conference on Signals, Systems, and Computers

Conference start date

2020-11-01

Conference finish date

2020-11-04

Title of proceedings

2020 54th Asilomar Conference on Signals, Systems, and Computers

Volume

00

Publication or Presentation Year

2020-11-01

Pagination

667-671

Publisher

IEEE

Publication status

Published

Usage metrics

    Conference papers

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC