High-Fidelity Speech Enhancement via Discrete Audio Tokens
This work addresses speech enhancement for applications requiring high-fidelity audio, offering a scalable and unified approach that improves upon existing methods.
The paper tackles the problem of speech enhancement by introducing DAC-SE1, a simplified language model-based framework that uses discrete high-resolution audio tokens, resulting in superior performance over state-of-the-art methods on objective metrics and human evaluations.
Recent autoregressive transformer-based speech enhancement (SE) methods have shown promising results by leveraging advanced semantic understanding and contextual modeling of speech. However, these approaches often rely on complex multi-stage pipelines and low sampling rate codecs, limiting them to narrow and task-specific speech enhancement. In this work, we introduce DAC-SE1, a simplified language model-based SE framework leveraging discrete high-resolution audio representations; DAC-SE1 preserves fine-grained acoustic details while maintaining semantic coherence. Our experiments show that DAC-SE1 surpasses state-of-the-art autoregressive SE methods on both objective perceptual metrics and in a MUSHRA human evaluation. We release our codebase and model checkpoints to support further research in scalable, unified, and high-quality speech enhancement.