English

SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings

Audio and Speech Processing 2026-07-16 v1 Sound

Abstract

We introduce the REAL-TSE Challenge, an IEEE SLT 2026 satellite challenge on target speaker extraction~(TSE) from real conversational recordings. Given a multi-speaker mixture and one or more enrollment utterances from a target speaker, participating systems must recover only the target speech. Unlike simulated read-speech benchmarks, REAL-TSE evaluates Mandarin and English recordings that contain natural overlap, reverberation, noise, channel mismatch, and conversational dynamics. The challenge defines two complementary tracks: an Online track for low-latency streaming extraction and an Offline track for full-context processing. Systems are evaluated with Token Error Rate (TER), Speaker Similarity (SpkSim), DNSMOS, and target-speaker activity F1. This overview paper describes the task definition, datasets, baselines, evaluation protocol, submitted systems, condition-wise findings, and lessons for future real-world TSE benchmarks.

Keywords

Cite

@article{arxiv.2607.15198,
  title  = {SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings},
  author = {Shuai Wang and Zihan Qian and Ke Zhang and Jiangyu Han and Zikai Liu and Xiaoyang Yu and Haoyu Li and Marc Delcroix and Kai Yu and Lei Xie and Ming Li and Haizhou Li},
  journal= {arXiv preprint arXiv:2607.15198},
  year   = {2026}
}

Comments

Overview paper of Real-TSE Challenge