# Adaptive Deterministic Flow Matching for Target Speaker Extraction

arXiv: https://arxiv.org/abs/2510.16995 · HTML: https://mlsanity.com/paper/2510.16995/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 19 Oct 2025.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise](https://mlsanity.com/paper/2208.09392/) (2022)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit](https://mlsanity.com/paper/2210.17016/) (2022)
- [Generative Pre-training for Speech with Flow Matching](https://mlsanity.com/paper/2310.16338/) (2023)
- [SpEx+: A Complete Time Domain Speaker Extraction Network](https://mlsanity.com/paper/2005.04686/) (2020)
- [Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration](https://mlsanity.com/paper/2211.02397/) (2022)
- [Cold Diffusion for Speech Enhancement](https://mlsanity.com/paper/2211.02527/) (2022)
- [Improving speaker discrimination of target speech extraction with time-domain SpeakerBeam](https://mlsanity.com/paper/2001.08378/) (2020)
- [FlowSE: Flow Matching-based Speech Enhancement](https://mlsanity.com/paper/2508.06840/) (2025)
- [Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration](https://mlsanity.com/paper/2409.16117/) (2024)
- [Target Speech Extraction with Conditional Diffusion Model](https://mlsanity.com/paper/2308.03987/) (2023)
- [SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline](https://mlsanity.com/paper/2505.19314/) (2025)
- [DDTSE: Discriminative Diffusion Model for Target Speech Extraction](https://mlsanity.com/paper/2309.13874/) (2023)
- [FlowTSE: Target Speaker Extraction with Flow Matching](https://mlsanity.com/paper/2505.14465/) (2025)

## Built on by (most cited first, 3 of 3)

- [MeanFlow-TSE: One-Step Generative Target Speaker Extraction with Mean Flow](https://mlsanity.com/paper/2512.18572/) (2025)
- [AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow](https://mlsanity.com/paper/2603.10701/) (2026)
- [FlowSep-RF: Rectified Flow Matching for Single-Channel Radio-Frequency Signal Separation](https://mlsanity.com/paper/2610.20269/) (2026)

## Abstract (arXiv)

Generative target speaker extraction (TSE) methods often produce more natural outputs than predictive models. Recent work based on diffusion or flow matching (FM) typically relies on a small, fixed number of reverse steps with a fixed step size. We introduce Adaptive Discriminative Flow Matching TSE (AD-FlowTSE), which extracts the target speech using an adaptive step size. We formulate TSE within the FM paradigm but, unlike prior FM-based speech enhancement and TSE approaches that transport between the mixture (or a normal prior) and the clean-speech distribution, we define the flow between the background and the source, governed by the mixing ratio (MR) of the source and background that creates the mixture. This design enables MR-aware initialization, where the model starts at an adaptive point along the background-source trajectory rather than applying the same reverse schedule across all noise levels. Experiments show that AD-FlowTSE achieves strong TSE with as few as a single step, and that incorporating auxiliary MR estimation further improves target speech accuracy. Together, these results highlight that aligning the transport path with the mixture composition and adapting the step size to noise conditions yields efficient and accurate TSE.