2020/11/02 by Zack Hodari, Hodari, Zack, Alexis Moinet +15
Engineering · #Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2011.01175
5 pages. Published in the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021)
arxiv created 2021/02/12 · arxiv updated 2021/02/15
Prosody is an integral part of communication, but remains an open problem in state-of-the-art speech synthesis. There are two major issues faced when modelling prosody: (1) prosody varies at a slower rate compared with other content in the acoustic signal (e.g. segmental information and background noise); (2) determining appropriate prosody without sufficient context is an ill-posed problem. In this paper, we propose solutions to both these issues. To mitigate the challenge of modelling a slow-varying signal, we learn to disentangle prosodic information using a word level representation. To alleviate the ill-posed nature of prosody modelling, we use syntactic and semantic information derived from text to learn a context-dependent prior over our prosodic space. Our Context-Aware Model of Prosody (CAMP) outperforms the state-of-the-art technique, closing the gap with natural speech by 26%. We also find that replacing attention with a jointly-trained duration model improves prosody significantly.