Authors: Kai Li, Wendi Sang, Jintao Cheng, Xiaolin Hu
Organizations: Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua University, Beijing, China · IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing, China · Chinese Institute for Brain Research (CIBR), Beijing, China
Real-world target speaker extraction (TSE) remains challenging because target speech, interference, and enrollment are recorded under mismatched acoustic conditions with reverberation, noise, and irregular conversational overlap. This paper describes the SonicAGI submission to the REAL-TSE Challenge (IEEE SLT 2026). We take a data-centric approach that combines fully simulated mixtures from clean speech with real meeting overlaps, and use a frozen offline enhancer to provide a denoised mirror of real targets for auxiliary supervision. For the online track, we introduce SwiftNet-Lookahead, which inserts a single bounded-lookahead module before a strictly causal iterative separator and keeps the total system latency at 96 ms. For the offline track, we use a frame-level enrollment cross-attention USEF-TFGridNet with a magnitude-domain fusion stage that trades off perceptual quality and speaker fidelity. In the official evaluation, SwiftNet-Lookahead ranks second in Track1 and USEF-TFGridNet ranks fifth in Track2, both exceeding the challenge baselines. These results suggest that real-data-oriented training and track-specific modeling are effective for conversational TSE.
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.
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.
While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications. Direct adaptation to streaming scenarios often leads to catastrophic inference performance degradation due to the severe mismatch between training and streaming inference. To bridge this gap, we present the first autoregressive (AR) models tailored for streaming TSE. Our approach introduces a Chunk-wise Interleaved Splicing Paradigm that ensures highly efficient and stable streaming inference. To ensure the coherence between the extracted speech segments, we design a historical context refinement mechanism that mitigates boundary discontinuities by leveraging historical information. Experiments on Libri2Mix show that while AR generative baseline exhibits performance degradation at low latencies, our approach maintains 100% stability and superior intelligibility. Furthermore, our streaming results are comparable to or even surpass offline baselines. Additionally, our model achieves a Real-Time-Factor (RTF) of 0.248 on consumer-level GPUs. This work provides empirical evidence that AR generative backbones are viable for latency-sensitive applications through the Chunk-wise Interleaved Splicing Paradigm.