# PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction

arXiv: https://arxiv.org/abs/2607.08111 · HTML: https://mlsanity.com/paper/2607.08111/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Deep clustering: Discriminative embeddings for segmentation and separation](https://mlsanity.com/paper/1508.04306/) (2015)
- [Cross-Entropy Loss Functions: Theoretical Analysis and Applications](https://mlsanity.com/paper/2304.07288/) (2023)
- [Attention is All You Need in Speech Separation](https://mlsanity.com/paper/2010.13154/) (2020)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit](https://mlsanity.com/paper/2210.17016/) (2022)
- [VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking](https://mlsanity.com/paper/1810.04826/) (2018)
- [M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge](https://mlsanity.com/paper/2110.07393/) (2021)
- [AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario](https://mlsanity.com/paper/2104.03603/) (2021)
- [Neural Target Speech Extraction: An Overview](https://mlsanity.com/paper/2301.13341/) (2023)
- [An Open source Implementation of ITU-T Recommendation P.808 with Validation](https://mlsanity.com/paper/2005.08138/) (2020)
- [DiPCo -- Dinner Party Corpus](https://mlsanity.com/paper/1909.13447/) (2019)
- [High Fidelity Speech Enhancement with Band-split RNN](https://mlsanity.com/paper/2212.00406/) (2022)
- [Multimodal Attention Fusion for Target Speaker Extraction](https://mlsanity.com/paper/2102.01326/) (2021)
- [USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction](https://mlsanity.com/paper/2409.02615/) (2024)
- [Improving curriculum learning for target speaker extraction with synthetic speakers](https://mlsanity.com/paper/2410.00811/) (2024)
- [MC-LExt: Multi-Channel Target Speaker Extraction with Onset-Prompted Speaker Conditioning Mechanism](https://mlsanity.com/paper/2510.15437/) (2025)

## Built on by (most cited first, 1 of 1)

- [DAVE: A Decoupled Audio-Visual Enhancement Framework for Real-World Speech Separation](https://mlsanity.com/paper/2608.09288/) (2026)

## Abstract (arXiv)

Training target speaker extraction (TSE) models for real conversational mixtures remains challenging because large-scale training corpora and clean target speech for supervision are unavailable. We present PS4, a proxy-supervised training framework for TSE in real conversational mixtures, with two main contributions. First, we construct a large-scale corpus of 71,771 training samples derived from four public datasets, covering both Chinese and English scenarios. Each sample contains an overlapping speech mixture, per-speaker enrollment audio, a ground-truth transcript, and frame-level voice activity labels. Second, we propose a proxy-supervised joint training strategy that fine-tunes a BSRNN-based TSE model using four complementary differentiable objectives: ASR cross-entropy, speaker similarity, frame-level voice activity detection, and perceptual audio quality. Starting from a publicly available pre-trained checkpoint, only the BSRNN separator is updated during fine-tuning. On the REAL-T challenge leaderboard, PS4 ranks 2nd overall, achieving the best speaker similarity and timing F1 among all submitted systems.