Singing Voice Synthesis

Jul 1, 2022
Go to Project Site Visit
Photo by rawpixel on Unsplash

This project includes some speech and music related research of Xiaobing.ai. The research topics cover text to speech, singing voice synthesis, music generation, etc.

NSS Deep Learning Avatar
Chang ZENG 曾畅　曾 暢 (ソウ チョウ)
Chang ZENG 曾畅　曾 暢 (ソウ チョウ)
Ph.D. Candidate

My research interests include speech signal processing, speaker recognition, antispoofing, and singing voice synthesis.

Publications

CrossSinger: A Cross-Lingual Multi-Singer High-Fidelity Singing Voice Synthesizer Trained on Monolingual Singers
This paper presents CrossSinger, a cross-lingual singing voice synthesizer based on Xiaoicesing2. It tackles the challenge of creating a multi-singer high-fidelity singing voice synthesis system with cross-lingual capabilities using only monolingual singers during training. The system unifies language representation, incorporates language information, and removes singer biases. Experimental results show that CrossSinger can synthesize high-quality songs for different singers in various languages, including code-switching cases.
Xintong Wang, Chang Zeng, Jun Chen, Chunhui Wang
PDF Cite Code Dataset Project ASRU2023 Link
CrossSinger: A Cross-Lingual Multi-Singer High-Fidelity Singing Voice Synthesizer Trained on Monolingual Singers
HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation
Generative adversarial network, Vocoder, High-fidelity, Singing voice generation.
Chunhui Wang, Chang Zeng, Jun Chen, Yuhao Wang, Xing He
PDF Cite Project DOI ArXiv Link
HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation
Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Network
This paper presents XiaoiceSing2, an enhanced singing voice synthesis system that addresses over-smoothing issues in middle- and high-frequency areas of mel-spectrograms. It employs a generative adversarial network (GAN) with improved model architecture to capture finer details.
Chunhui Wang, Chang Zeng, Xing He
PDF Cite Code Dataset Project DOI Interspeech2023
Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Network