AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912961586528256 |
|---|---|
| author | Li, Duojia Zhang, Shuhan Qian, Zihan Wu, Wenxuan Wang, Shuai Hong, Qingyang Li, Lin Li, Haizhou |
| author_facet | Li, Duojia Zhang, Shuhan Qian, Zihan Wu, Wenxuan Wang, Shuai Hong, Qingyang Li, Lin Li, Haizhou |
| contents | In target speaker extraction (TSE), we aim to recover target speech from a multi-talker mixture using a short enrollment utterance as reference. Recent studies on diffusion and flow-matching generators have improved target-speech fidelity. However, multi-step sampling increases latency, and one-step solutions often rely on a mixture-dependent time coordinate that can be unreliable for real-world conversations. We present AlphaFlowTSE, a one-step conditional generative model trained with a Jacobian-vector product (JVP)-free AlphaFlow objective. AlphaFlowTSE learns mean-velocity transport along a mixture-to-target trajectory starting from the observed mixture, eliminating auxiliary mixing-ratio prediction, and stabilizes training by combining flow matching with an interval-consistency teacher-student target. Experiments on Libri2Mix and REAL-T confirm that AlphaFlowTSE improves target-speaker similarity and real-mixture generalization for downstream automatic speech recognition (ASR). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10701 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow Li, Duojia Zhang, Shuhan Qian, Zihan Wu, Wenxuan Wang, Shuai Hong, Qingyang Li, Lin Li, Haizhou Sound Artificial Intelligence In target speaker extraction (TSE), we aim to recover target speech from a multi-talker mixture using a short enrollment utterance as reference. Recent studies on diffusion and flow-matching generators have improved target-speech fidelity. However, multi-step sampling increases latency, and one-step solutions often rely on a mixture-dependent time coordinate that can be unreliable for real-world conversations. We present AlphaFlowTSE, a one-step conditional generative model trained with a Jacobian-vector product (JVP)-free AlphaFlow objective. AlphaFlowTSE learns mean-velocity transport along a mixture-to-target trajectory starting from the observed mixture, eliminating auxiliary mixing-ratio prediction, and stabilizes training by combining flow matching with an interval-consistency teacher-student target. Experiments on Libri2Mix and REAL-T confirm that AlphaFlowTSE improves target-speaker similarity and real-mixture generalization for downstream automatic speech recognition (ASR). |
| title | AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2603.10701 |