Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation
This work addresses the need for more efficient and streamlined text-to-speech synthesis systems, though it is incremental as it builds on existing audio token modeling frameworks.
The paper tackled the problem of simplifying text-to-speech synthesis by introducing a semantic knowledge distillation method that enables high-quality speech generation in a single stage, improving speech quality, intelligibility, and speaker similarity compared to a single-stage baseline and narrowing the gap with two-stage systems.
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.