AdaDurIAN: Few-shot Adaptation for Neural Text-to-Speech with DurIAN

By Zewang Zhang, Qiao Tian, Heng Lu, Ling Chen, Shan Liu. 2020

27 citations recorded by the source corpus.

This paper investigates how to leverage a DurIAN-based average model to enable a new speaker to have both accurate pronunciation and fluent cross-lingual speaking with very limited monolingual data. A weakness of the recently proposed end-to-end text-to-speech (TTS) systems is that robust alignment is hard to achieve, which hinders it to scale well with very limited data. To cope with this issue, we introduce AdaDurIAN by training an improved DurIAN-based average model and leverage it to few-shot learning with the shared speaker-independent content encoder across different speakers. Several few-shot learning tasks in our experiments show AdaDurIAN can outperform the baseline end-to-end system by a large margin. Subjective evaluations also show that AdaDurIAN yields higher mean opinion score (MOS) of naturalness and more preferences of speaker similarity. In addition, we also apply AdaDurIAN to emotion transfer tasks and demonstrate its promising performance.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Sung Ju Hwang
6. Xinyu Yang
7. Zhaoxi Mu
8. Yizhuo Dong

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, background): “, decoder) [234, 439], or only speaker embedding [9, 43, 39] can be fine-tuned.”
• Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation (2021, background): “A popular approach is to train the model on a large multi-speakers dataset and then fine-tune the whole model (Chen et al., 2019; Arik et al., 2018) or only parts of the model (Moss et al., 2020; Zhang et al., 2020; Chen et al., 2021).”
• Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “Fine-tuning can be applied to the speaker embedded vector [4, 204], part of the model [265], or the whole model [4].”
• FeatherTTS: Robust and Efficient attention based Neural TTS (2020, methodology): “Other experimental setups are the same as AdaDurIAN [20] if not specified.”