Audio token modeling has become a powerful framework for speech synthesis, with two-stage approaches employing semantic tokens remaining prevalent. In this paper, we aim to simplify this process by introducing a semantic knowledge distillation method that enables high-quality speech generation in a single stage. Our proposed model improves speech quality, intelligibility, and speaker similarity compared to a single-stage baseline. Although two-stage systems still lead in intelligibility, our model significantly narrows the gap while delivering comparable speech quality. These findings showcase the potential of single-stage models to achieve efficient, high-quality TTS with a more compact and streamlined architecture.
@article{arxiv.2409.11003,
title = {Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation},
author = {Gerard I. Gállego and Roy Fejgin and Chunghsin Yeh and Xiaoyu Liu and Gautam Bhattacharya},
journal= {arXiv preprint arXiv:2409.11003},
year = {2024}
}