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

Emotion Controllable Speech Synthesis Using Emotion-unlabeled Dataset With The Assistance Of Cross-domain Speech Emotion Recognition

Citation Author(s):
Xiong Cai; Dongyang Dai; Zhiyong Wu
Submitted by:
xiong cai
Last updated:
18 June 2021 - 3:40am
Document Type:
Poster
Document Year:
2021
Presenters:
xiong cai
Paper Code:
1863
 

Neural text-to-speech (TTS) approaches generally require a huge number of high quality speech data, which makes it difficult to obtain such a dataset with extra emotion labels. In this paper, we propose a novel approach for emotional TTS synthesis on a TTS dataset without emotion labels. Specifically, our proposed method consists of a cross-domain speech emotion recognition (SER) model and an emotional TTS model. Firstly, we train the cross-domain SER model on both SER and TTS datasets. Then, we use emotion labels on the TTS dataset predicted by the trained SER model to build an auxiliary SER task and jointly train it with the TTS model. Experimental results show that our proposed method can generate speech with the specified emotional expressiveness and nearly no hindering on the speech quality.

up
0 users have voted: