11 papers
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
Wenxi Chen, Dongya Jia, Yushen Chen +11
Recently, diffusion models operating on VAE latents or mel-spectrograms have become the dominant paradigm for zero-shot TTS. Although these compressed representations improve gener…
On the Distillation Loss Functions of Speech VAE for Unified Reconstruction, Understanding, and Generation
Changhao Cheng, Wei Wang, Wangyou Zhang +4
Continuous speech representations based on Variational Autoencoders (VAEs) have emerged as a promising alternative to traditional spectrogram or discrete token based features for s…
Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation
Xueyao Zhang, Junan Zhang, Yuancheng Wang +5
Controllable human voice generation, particularly for expressive domains like singing, remains a significant challenge. This paper introduces Vevo2, a unified framework for control…
DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
Dongya Jia, Zhuo Chen, Jiawei Chen +8
Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models…
SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
Xueyao Zhang, Chaoren Wang, Huan Liao +8
Aligning large generative models with human feedback is a critical challenge. In speech synthesis, this is particularly pronounced due to the lack of a large-scale human preference…
DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation
Yakun Song, Xiaobin Zhuang, Jiawei Chen +8
Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under d…