TTS

Addressing Index Collapse of Large-Codebook Speech Tokenizer with Dual-Decoding Product-Quantized Variational Auto-Encoder
Conference paper accepted by IEEE SLT 2024.
Haohan Guo, Fenglong Xie, Dongchao Yang, Hui Lu, Xixin Wu, Helen Meng
PDF Cite
SoCodec: A Semantic-Ordered Multi-Stream Speech Codec for Efficient Language Model Based Text-to-Speech Synthesis
Conference paper accepted by IEEE SLT 2024.
Haohan Guo, Fenglong Xie, Kun Xie, Dongchao Yang, Dake Guo, Xixin Wu, Helen Meng
PDF Cite Code Project
QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning
Journal paper accepted by IEEE TASLP (2024).
Haohan Guo, Fenglong Xie, Jiawen Kang, Yujia Xiao, Xixin Wu, Helen Meng
PDF Cite Project
MSMC-TTS: Multi-Stage Multi-Codebook VQ-VAE based Neural TTS
Journal paper accepted by TASLP
Haohan Guo, Fenglong Xie, Frank K. Soong, Xixin Wu, Helen Meng
PDF Cite
MSMC-TTS: Multi-Stage Multi-Codebook VQ-VAE based Neural TTS
A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS
Conference paper accepted by INTERSPEECH 2022
Haohan Guo, Fenglong Xie, Frank K. Soong, Xixin Wu, Helen Meng
PDF Cite
A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS