Training Multi-speaker Neural Text-to-speech Systems Using Speaker-imbalanced Speech Corpora
2019 · Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, et al.
Abstract
When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies have shown that neural multi-speaker TTS model trained with a small amount data from multiple speakers combined can generate synthetic speech with better quality and stability than a speaker-dependent one. However when the amount of data from each speaker is highly unbalanced, the best approach to make use of the excessive data remains unknown. Our experiments showed that simply combining all available data from every speaker to train a multi-speaker model produces better than or at least similar performance to its speaker-dependent counterpart. Moreover by using an ensemble multi-speaker model, in which each subsystem is trained on a subset of available data, we can further improve the quality of the synthetic speech especially for underrepresented s
Authors
(none)
Tags
Stats
Related papers
- Combining Speakers Of Multiple Languages To Improve Quality Of Neural Voices (2021)5.24
- Modeling Multi-speaker Latent Space To Improve Neural TTS: Quick Enrolling New Speaker And Enhancing Premium Voice (2018)0.00
- Speaker Verification-derived Loss And Data Augmentation For Dnn-based Multispeaker Speech Synthesis (2021)3.58
- Semi-supervised Learning For Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation (2020)5.24
- Improving The Quality Of Neural TTS Using Long-form Content And Multi-speaker Multi-style Modeling (2022)3.58
- Efficient Neural Speech Synthesis For Low-resource Languages Through Multilingual Modeling (2020)8.60
- Effect Of Data Reduction On Sequence-to-sequence Neural TTS (2018)9.76
- Multi-task Adversarial Training Algorithm For Multi-speaker Neural Text-to-speech (2022)0.00