Paper Info
Title
HIGH-INTELLIGIBILITY SPEECH SYNTHESIS FOR DYSARTHRIC SPEAKERS WITH LPCNET-BASED TTS AND CYCLEVAE-BASED VC
Abstract
This paper presents a high-intelligibility speech synthesis method for persons with dysarthria caused by athetoid cerebral palsy. The muscular control of such speakers is unstable because of their athetoid symptoms, and their pronunciation is unclear, which makes it difficult for them to communicate. In this paper, we present a method for generating highly intelligible speech that preserves the individuality of dysarthric speakers by combining Transformer-TTS, CycleVAE-VC, and a LPCNet vocoder. Rather than repairing prosody from the dysarthric speech, this method transfers the dysarthric speaker's individuality to the speech of a healthy person generated by TTS synthesis. This task is both important and challenging. From the results of our evaluation experiments, we confirmed that the proposed method can partially transfer the individuality of the target dysarthric speaker while maintaining the intelligibility of the source speech.
Year
DOI
Venue
2021
10.1109/ICASSP39728.2021.9414136
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)
Keywords
DocType
Citations 
dysarthria, speech synthesis, text-to-speech, voice conversion, neural vocoder
Conference
0
PageRank 
References 
Authors
0.34
0
7
Name
Order
Citations
PageRank
Keisuke Matsubara100.68
Takuma Okamoto243.22
Ryoichi Takashima39512.16
Tetsuya Takiguchi4858.77
Tomoki Toda51874167.18
Yoshinori Shiga64513.35
Hisashi Kawai725054.04