Frozen-LM Conditioning

GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model

Announce Type: replace-cross Abstract: Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech. We propose GenTSE, a two-stage decoder-only generative LM for TSE: Stage-1 predicts coarse semantic tokens, and Stage-2 generates fine acoustic tokens. Separating semantics and acoustics stabilizes decoding and yields more accurate target speech.