Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System using Deep Recurrent Neural Networks

Cassia Valentini Botinhao, Xin Wang, Shinji Takaki, Junichi Yamagishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Quality of text-to-speech voices built from noisy recordings is diminished. In order to improve it we propose the use of a recurrent neural network to enhance acoustic parameters prior to training. We trained a deep recurrent neural network using a parallel database of noisy and clean acoustics parameters as input and output of the network. The database consisted of multiple speakers and diverse noise conditions. We investigated using text-derived features as an additional input of the network. We processed a noisy database of two other speakers using this network and used its output to train an HMM acoustic text-to-synthesis model for each voice. Listening experiment results showed that the voice built with enhanced parameters was ranked significantly higher than the ones trained with noisy speech and speech that has been enhanced using a conventional enhancement system. The text-derived features improved results only for the female voice, where it was ranked as highly as a voice trained with clean speech.
Original languageEnglish
Title of host publicationProceedings of Interspeech 2016
Place of PublicationSan Francisco, United States
Number of pages5
Publication statusPublished - 8 Sept 2016
EventInterspeech 2016 - San Francisco, United States
Duration: 8 Sept 201612 Sept 2016

Publication series

PublisherInternational Speech Communication Association
ISSN (Print)1990-9772


ConferenceInterspeech 2016
Country/TerritoryUnited States
CitySan Francisco
Internet address


Dive into the research topics of 'Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System using Deep Recurrent Neural Networks'. Together they form a unique fingerprint.

Cite this