Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation

Dimitri Kanvesky
Dimitri Kanvesky
Ye Jia
Ye Jia

Conference of the International Speech Communication Association, 2019.

Cited by: 31|Bibtex|Views58|DOI:https://doi.org/10.21437/interspeech.2019-1789
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We describe Parrotron, an end-to-end-trained speech-to-speech conversion model that maps an input spectrogram directly to another spectrogram, without utilizing any intermediate discrete representation. The network is composed of an encoder, spectrogram and phoneme decoders, followed by a vocoder to synthesize a time-domain waveform. We d...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments