Time-domain speech enhancement using generative adversarial networks
Authors:
- Santiago PascualSPSantiago Pascual
- Joan SerràJSJoan Serrà
- Antonio BonafonteABAntonio Bonafonte
- 1 November 2019
- journal article
- research article
- Published by Elsevier in Speech Communication
- Vol. 114, 10-21
Abstract
No abstract availableKeywords
Funding Information
- European Regional Development Fund (TEC2015-69266-P)
This publication has 21 references indexed in Scilit:
- The diverse environments multi-channel acoustic noise database: A database of multichannel environmental noise recordingsThe Journal of the Acoustical Society of America, 2013
- Speaking-aid systems using GMM-based voice conversion for electrolaryngeal speechSpeech Communication, 2012
- The importance of phase in speech enhancementSpeech Communication, 2011
- Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture modelSpeech Communication, 2008
- Development of a (silent) speech recognition system for patients following laryngectomyMedical Engineering & Physics, 2007
- Long Short-Term MemoryNeural Computation, 1997
- A signal subspace approach for speech enhancementIEEE Transactions on Speech and Audio Processing, 1995
- Statistical-model-based speech enhancement systemsProceedings of the IEEE, 1992
- The unimportance of phase in speech enhancementIEEE Transactions on Acoustics, Speech, and Signal Processing, 1982
- All-pole modeling of degraded speechIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978