{"ID":6497855,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-14T01:36:59.12045529Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.09043","arxiv_id":"2607.09043","title":"Technical Report for MERL's Real-TSE Challenge Submission","abstract":"Target speech extraction (TSE) has largely been dominated by neural network-based approaches trained and evaluated on synthetic fully overlapped data. The Real-TSE Challenge aims to advance performance on real-world far-field noisy and reverberant recordings. This technical report describes MERL's submission to the Real-TSE Challenge. Rather than proposing a novel model architecture, we built upon the baseline model and focused primarily on data preparation and cleaning. Our system was trained in four stages, beginning with pre-training on fully overlapped mixtures and simulated multi-talker conversations with noise and reverberation applied to both the mixture and the enrollment utterances. We then adapted the model to real-world conditions using noisy far-field recordings with pseudo-targets derived from processed close-talk microphone signals. Our submission achieved first place in the second track, demonstrating the critical importance of high-quality data preparation. Furthermore, we observed that DNSMOS and speaker similarity are susceptible to over-optimization, motivating an investigation of their robustness using adversarial attacks. The results show that both metrics can be driven to extreme values without degrading the token error rate or the VAD-based F1 score.","short_abstract":"Target speech extraction (TSE) has largely been dominated by neural network-based approaches trained and evaluated on synthetic fully overlapped data. The Real-TSE Challenge aims to advance performance on real-world far-field noisy and reverberant recordings. This technical report describes MERL's submission to the Rea...","url_abs":"https://arxiv.org/abs/2607.09043","url_pdf":"https://arxiv.org/pdf/2607.09043v1","authors":"[\"Dominik Klement\",\"Yoshiki Masuyama\",\"Christoph Boeddeker\",\"Kohei Saijo\",\"Julius Richter\",\"Gordon Wichern\",\"Jonathan Le Roux\"]","published":"2026-07-10T02:18:02Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[\"Large Language Model\"]","has_code":false}