35 citations · 52 across the 8 of their papers we have counts for
8 papers
Robust MelGAN: A robust universal neural vocoder for high-fidelity TTS
Kun Song, Jian Cong, Xinsheng Wang +4
In current two-stage neural text-to-speech (TTS) paradigm, it is ideal to have a universal neural vocoder, once trained, which is robust to imperfect mel-spectrogram predicted from…
DSPGAN: a GAN-based universal vocoder for high-fidelity TTS by time-frequency domain supervision from DSP
Kun Song, Yongmao Zhang, Yi Lei +5
Recent development of neural vocoders based on the generative adversarial neural network (GAN) has shown obvious advantages of generating raw waveform conditioned on mel-spectrogra…
Glow-WaveGAN 2: High-quality Zero-shot Text-to-speech Synthesis and Any-to-any Voice Conversion
Yi Lei, Shan Yang, Jian Cong +2
The zero-shot scenario for speech generation aims at synthesizing a novel unseen voice with only one utterance of the target speaker. Although the challenges of adapting new voices…
AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation
Kun Song, Heyang Xue, Xinsheng Wang +6
Speaker adaptation in text-to-speech synthesis (TTS) is to finetune a pre-trained TTS model to adapt to new target speakers with limited data. While much effort has been conducted…
NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
Xu Tan, Jiawei Chen, Haohe Liu +11
Text to speech (TTS) has made rapid progress in both academia and industry in recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality…
VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
Yongmao Zhang, Jian Cong, Heyang Xue +3
In this paper, we propose VISinger, a complete end-to-end high-quality singing voice synthesis (SVS) system that directly generates audio waveform from lyrics and musical score. Ou…
Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis
Jian Cong, Shan Yang, Lei Xie +1
Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectr…
Data Efficient Voice Cloning from Noisy Samples with Domain Adversarial Training
Jian Cong, Shan Yang, Lei Xie +2
Data efficient voice cloning aims at synthesizing target speaker's voice with only a few enrollment samples at hand. To this end, speaker adaptation and speaker encoding are two ty…