Speaker Representations for Speaker Adaptation in Multiple Speakers' BLSTM-RNN-Based Speech Synthesis

By Yi Zhao, Daisuke Saito, Nobuaki Minematsu. 2016

21 citations recorded by the source corpus.

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. Junichi Yamagishi
6. Xin Eric Wang
7. Hieu-Thi Luong
8. Sheng Zhao

In Signal Processing

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Junichi Yamagishi
5. Frank K. Soong
6. Xin Eric Wang
7. Hieu-Thi Luong
8. Shinji Takaki

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, background): “, a lot of works in statistic parametric speech synthesis have studied voice adaptation [77, 386, 443, 65, 122], and the recent voice cloning challenge also attracts a lot of participants [388, 118, 331, 45].”
• Wasserstein GAN and Waveform Loss-Based Acoustic Model Training for Multi-Speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder (2018, background): “[22] examined various speaker identity representations for multi-speaker synthesis and showed that multi-speaker systems trained with less of the target speaker’s data can even outperform single speaker speech synthesis, which uses a larger amount of the target speaker’s data.”
• Linear Networks Based Speaker Adaptation for Speech Synthesis (2018, background): “Also, in some multi-speaker speech synthesis systems, i-vector and speaker code representing speaker [15, 16] are combined with linguistic features as input features for the neural network based acoustic model.”
• Speaker Adaptation in DNN-Based Speech Synthesis Using d-Vectors (2017, background): “In [12], i-vectors have been shown to improve the quality of synthetic speech and enable to control the speaker identity.”
• Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora (2019, methodology): “The multi-speaker model is simple to set up [12, 13] and can generate more stable speech waveforms than those of the speaker-dependent model when the amount of the target speaker’s data is limited [10].”