Paper Info
Title
Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech Synthesis.
Abstract
Naturalness and expressiveness are crucial for audiobook speech synthesis, but now are limited by the averaged global-scale speaking style representation. In this paper, we propose an unsupervised multi-scale context-sensitive text-to-speech model for audiobooks. A multi-scale hierarchical context encoder is specially designed to predict both global-scale context style embedding and local-scale context style embedding from a wider context of input text in a hierarchical manner. Likewise, a multi-scale reference encoder is introduced to extract reference style embeddings at both global and local scales from the reference speech, which is used to guide the prediction of speaking styles. On top of these, a bi-reference attention mechanism is used to align both local-scale reference style embedding sequence and local-scale context style embedding sequence with corresponding phoneme embedding sequence. Both objective and subjective experiment results on a real-world multi-speaker Mandarin novel audio dataset demonstrate the excellent performance of our proposed method over all baselines in terms of naturalness and expressiveness of the synthesized speech.
Year
Venue
DocType
2022
International Conference on Computational Linguistics
Conference
Volume
Citations 
PageRank 
Proceedings of the 29th International Conference on Computational Linguistics
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Xueyuan Chen100.34
Shun Lei201.35
Wu Zhiyong311936.98
Dong Xu471.23
Weifeng Zhao511.39
Helen M. Meng61078172.82