Investigation Of Enhanced Tacotron Text-to-speech Synthesis Systems With Self-attention For Pitch Accent Language
2018 · Yusuke Yasuda, Xin Wang, Shinji Takaki, et al.
Abstract
End-to-end speech synthesis is a promising approach that directly converts raw text to speech. Although it was shown that Tacotron2 outperforms classical pipeline systems with regards to naturalness in English, its applicability to other languages is still unknown. Japanese could be one of the most difficult languages for which to achieve end-to-end speech synthesis, largely due to its character diversity and pitch accents. Therefore, state-of-the-art systems are still based on a traditional pipeline framework that requires a separate text analyzer and duration model. Towards end-to-end Japanese speech synthesis, we extend Tacotron to systems with self-attention to capture long-term dependencies related to pitch accents and compare their audio quality with classical pipeline systems under various conditions to show their pros and cons. In a large-scale listening test, we investigated the impacts of the presence of accentual-type labels, the use of force or predicted alignments, and aco
Authors
(none)
Tags
Stats
Related papers
- Tacotron: Towards End-to-end Speech Synthesis (2017)0.00
- Investigation Of Japanese Png BERT Language Model In Text-to-speech Synthesis For Pitch Accent Language (2022)8.09
- Investigation Of Learning Abilities On Linguistic Features In Sequence-to-sequence Text-to-speech Synthesis (2020)8.82
- Non-attentive Tacotron: Robust And Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling (2020)0.00
- Towards End-to-end Prosody Transfer For Expressive Speech Synthesis With Tacotron (2018)0.00
- Semi-supervised Training For Improving Data Efficiency In End-to-end Speech Synthesis (2018)13.28
- Training Text-to-speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks (2022)7.16
- Modeling Prosodic Phrasing With Multi-task Learning In Tacotron-based TTS (2020)9.41