English

Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis

Audio and Speech Processing 2022-04-08 v1 Multimedia

Abstract

In this paper, we propose a novel prosody disentangle method for prosodic Text-to-Speech (TTS) model, which introduces the vector quantization (VQ) method to the auxiliary prosody encoder to obtain the decomposed prosody representations in an unsupervised manner. Rely on its advantages, the speaking styles, such as pitch, speaking velocity, local pitch variance, etc., are decomposed automatically into the latent quantize vectors. We also investigate the internal mechanism of VQ disentangle process by means of a latent variables counter and find that higher value dimensions usually represent prosody information. Experiments show that our model can control the speaking styles of synthesis results by directly manipulating the latent variables. The objective and subjective evaluations illustrated that our model outperforms the popular models.

Keywords

Cite

@article{arxiv.2204.03238,
  title  = {Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis},
  author = {Yutian Wang and Yuankun Xie and Kun Zhao and Hui Wang and Qin Zhang},
  journal= {arXiv preprint arXiv:2204.03238},
  year   = {2022}
}

Comments

accepted by IEEE International Conference on Multimedia and Expo 2022 (ICME2022)

R2 v1 2026-06-24T10:40:47.571Z