Sorry, you need to enable JavaScript to visit this website.

Cyborg Speech: Deep Multilingual Speech Synthesis for Generating Segmental Foreign Accent with Natural Prosody

Citation Author(s):
Jaime Lorenzo-Trueba, Mariko Kondo, Junichi Yamagishi
Submitted by:
Gustav Eje Henter
Last updated:
29 April 2018 - 1:59pm
Document Type:
Presentation Slides
Document Year:
2018
Event:
Presenters:
Gustav Eje Henter
Paper Code:
SP-L2.5
 

We describe a new application of deep-learning-based speech synthesis, namely multilingual speech synthesis for generating controllable foreign accent. Specifically, we train a DBLSTM-based acoustic model on non-accented multilingual speech recordings from a speaker native in several languages. By copying durations and pitch contours from a pre-recorded utterance of the desired prompt, natural prosody is achieved. We call this paradigm "cyborg speech" as it combines human and machine speech parameters. Segmentally accented speech is produced by interpolating specific quinphone linguistic features towards phones from the other language that represent non-native mispronunciations. Experiments on synthetic American-English-accented Japanese speech show that subjective synthesis quality matches monolingual synthesis, that natural pitch is maintained, and that naturalistic phone substitutions generate output that is perceived as having an American foreign accent, even though only non-accented training data was used.

up
0 users have voted: