AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow

• URL: http://arxiv.org/abs/2603.10701v1
• Date: Wed, 11 Mar 2026 12:14:25 GMT
• Title: AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow
• Abstract summary: We present a one-step conditional generative model trained with a Jacobian-vector product (JVP)-free AlphaFlow objective.<n>Experiments on Libri2Mix and REAL-T confirm that AlphaFlowTSE improves target-speaker similarity and real-mixture for downstream automatic speech recognition (ASR)
• Score: 39.38826937846528
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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).

Related papers

• DiffusionGemma Technical Report [72.10570774996219]
  We introduce DiffusionGemma, a language model that uses discrete diffusion to generate text at exceptionally high speed.<n>Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel.<n>Our compute-efficient two-stage training pipeline uses fewer than 10% of the starting AR model's total training token budget.
  arXiv  Detail & Related papers  (2026-07-31T16:11:46Z)
• Drax: Speech Recognition with Discrete Flow Matching [26.991421132974097]
  Diffusion and flow-based non-autoregressive (NAR) models have shown strong promise in large language modeling.<n>We propose Drax, a discrete flow matching framework for automatic speech recognition (ASR)<n>We construct an audio-conditioned probability path that guides the model through trajectories resembling likely intermediate inference errors.
  arXiv  Detail & Related papers  (2025-10-05T11:38:01Z)
• FlowTSE: Target Speaker Extraction with Flow Matching [16.054014378418316]
  FlowTSE is a simple yet effective TSE approach based on conditional flow matching.<n>For tasks where phase reconstruction is crucial, we propose a novel vocoder conditioned on the complex STFT of the mixed signal.
  arXiv  Detail & Related papers  (2025-05-20T15:01:30Z)
• Adversarial AutoMixup [50.1874436169571]
  We propose AdAutomixup, an adversarial automatic mixup augmentation approach. It generates challenging samples to train a robust classifier for image classification. Our approach outperforms the state of the art in various classification scenarios.
  arXiv  Detail & Related papers  (2023-12-19T08:55:00Z)
• Expeditious Saliency-guided Mix-up through Random Gradient Thresholding [89.59134648542042]
  Mix-up training approaches have proven to be effective in improving the generalization ability of Deep Neural Networks. In this paper, inspired by the superior qualities of each direction over one another, we introduce a novel method that lies at the junction of the two routes. We name our method R-Mix following the concept of "Random Mix-up" In order to address the question of whether there exists a better decision protocol, we train a Reinforcement Learning agent that decides the mix-up policies.
  arXiv  Detail & Related papers  (2022-12-09T14:29:57Z)
• Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem [65.25725367771075]
  This study demonstrates, for the first time, that the synthesis-based approach can also perform well on this problem. Specifically, we propose a novel speech separation/enhancement model based on the recognition of discrete symbols. By utilizing the synthesis model with the input of discrete symbols, after the prediction of discrete symbol sequence, each target speech could be re-synthesized.
  arXiv  Detail & Related papers  (2021-12-17T08:35:40Z)
• SMILE: Self-Distilled MIxup for Efficient Transfer LEarning [42.59451803498095]
  In this work, we propose SMILE - Self-Distilled Mixup for EffIcient Transfer LEarning. With mixed images as inputs, SMILE regularizes the outputs of CNN feature extractors to learn from the mixed feature vectors of inputs. The triple regularizer balances the mixup effects in both feature and label spaces while bounding the linearity in-between samples for pre-training tasks.
  arXiv  Detail & Related papers  (2021-03-25T16:02:21Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.