Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations
By: Yichen Han , Xiaoyang Hao , Keming Chen and more
Potential Business Impact:
Makes computer voices sound more real and expressive.
Text-to-speech (TTS) synthesis has seen renewed progress under the discrete modeling paradigm. Existing autoregressive approaches often rely on single-codebook representations, which suffer from significant information loss. Even with post-hoc refinement techniques such as flow matching, these methods fail to recover fine-grained details (e.g., prosodic nuances, speaker-specific timbres), especially in challenging scenarios like singing voice or music synthesis. We propose QTTS, a novel TTS framework built upon our new audio codec, QDAC. The core innovation of QDAC lies in its end-to-end training of an ASR-based auto-regressive network with a GAN, which achieves superior semantic feature disentanglement for scalable, near-lossless compression. QTTS models these discrete codes using two innovative strategies: the Hierarchical Parallel architecture, which uses a dual-AR structure to model inter-codebook dependencies for higher-quality synthesis, and the Delay Multihead approach, which employs parallelized prediction with a fixed delay to accelerate inference speed. Our experiments demonstrate that the proposed framework achieves higher synthesis quality and better preserves expressive content compared to baseline. This suggests that scaling up compression via multi-codebook modeling is a promising direction for high-fidelity, general-purpose speech and audio generation.
Similar Papers
Comprehend and Talk: Text to Speech Synthesis via Dual Language Modeling
Sound
Makes computer voices sound more natural and human.
BridgeCode: A Dual Speech Representation Paradigm for Autoregressive Zero-Shot Text-to-Speech Synthesis
Sound
Makes talking computers sound more natural, faster.
Parallel GPT: Harmonizing the Independence and Interdependence of Acoustic and Semantic Information for Zero-Shot Text-to-Speech
Audio and Speech Processing
Makes computer voices sound more human and real.