Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora

By Hieu-Thi Luong, Xin Eric Wang, Junichi Yamagishi, Nobuyuki Nishizawa. 2019

24 citations recorded by the source corpus.

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 speakers whose training data is limited.

Subfields: Artificial Intelligence, Signal Processing

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. Rui Liu
6. Sheng Zhao
7. Haizhou Li
8. Berrak Sisman

In Signal Processing

1. Xu Tan
2. Tie-Yan Liu
3. Tao Qin
4. Frank K. Soong
5. Rui Liu
6. Berrak Sisman
7. Haizhou Li
8. Guanglai Gao

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “Techniques Data Work Self-supervised Training Unpaired text or speech [51, 368, 433, 78, 140, 346, 197, 352, 71] Cross-lingual Transfer Paired text and speech [42, 390, 12, 60, 271, 105] Cross-speaker Transfer Paired text and speech [216, 125, 59, 39] Speech chain/Back transformation Unpaired text o”
• Modeling Prosodic Phrasing With Multi-Task Learning in Tacotron-Based TTS (2020, background): “The key idea is to integrate the conventional TTS pipeline into a unified network and learn the mapping directly from the text-waveform pair [8]– [10].”
• Teacher-Student Training For Robust Tacotron-Based TTS (2019, methodology): “In these techniques, the key idea is to integrate the conventional TTS pipeline into a unified network and learn the mapping directly from the < text, wav > pair [7–10].”