Speaker-adaptive Neural Vocoders For Parametric Speech Synthesis Systems
2018 · Eunwoo Song, Jin-Seob Kim, Kyungguen Byun, et al.
Abstract
This paper proposes speaker-adaptive neural vocoders for parametric text-to-speech (TTS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an autoregressive framework. However, it remains a challenge to synthesize high-quality speech when the amount of a target speaker's training data is insufficient. To generate more natural speech signals with the constraint of limited training data, we propose a speaker adaptation task with an effective variation of neural vocoding models. In the proposed method, a speaker-independent training method is applied to capture universal attributes embedded in multiple speakers, and the trained model is then optimized to represent the specific characteristics of the target speaker. Experimental results verify that the proposed TTS systems with speaker-adaptive neural vocoders outperform those with traditional source-filter model-based vocoders and those with WaveNet vocoders, train
Authors
(none)
Tags
Stats
Related papers
- Generative Adversarial Network Based Speaker Adaptation For High Fidelity Wavenet Vocoder (2018)5.84
- Sample Efficient Adaptive Text-to-speech (2018)0.00
- Speaker Independence Of Neural Vocoders And Their Effect On Parametric Resynthesis Speech Enhancement (2019)6.34
- Wasserstein GAN And Waveform Loss-based Acoustic Model Training For Multi-speaker Text-to-speech Synthesis Systems Using A Wavenet Vocoder (2018)12.61
- Transfer Learning From Speaker Verification To Multispeaker Text-to-speech Synthesis (2018)0.00
- A Unified Speaker Adaptation Method For Speech Synthesis Using Transcribed And Untranscribed Speech With Backpropagation (2019)0.00
- Towards Robust Neural Vocoding For Speech Generation: A Survey (2019)0.00
- A Comparison Of Recent Waveform Generation And Acoustic Modeling Methods For Neural-network-based Speech Synthesis (2018)11.76