# Cross-Talk Speech Reduction, by Separation, for Separation

arXiv: https://arxiv.org/abs/2605.19695 · HTML: https://mlsanity.com/paper/2605.19695/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speaker recognition and diarization, one of 11 directions in Speech and audio language models.
- Builds on 52 of its 69 references that are in the map.
- First posted on arXiv 19 May 2026.

## Placed in

- Speech and audio language models / [Speaker recognition and diarization](https://mlsanity.com/speech/speaker-recognition-and-diarization/)

## Builds on (most cited first, 30 of 52)

- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [pyannote.audio: neural building blocks for speaker diarization](https://mlsanity.com/paper/1911.01255/) (2019)
- [The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines](https://mlsanity.com/paper/1803.10609/) (2018)
- [Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks](https://mlsanity.com/paper/1703.06284/) (2017)
- [Continuous speech separation: dataset and analysis](https://mlsanity.com/paper/2001.11482/) (2020)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [Integrating end-to-end neural and clustering-based diarization: Getting the best of both worlds](https://mlsanity.com/paper/2010.13366/) (2020)
- [Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST](https://mlsanity.com/paper/2509.14128/) (2025)
- [Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis](https://mlsanity.com/paper/2011.02014/) (2020)
- [The Second DIHARD Diarization Challenge: Dataset, task, and baselines](https://mlsanity.com/paper/1906.07839/) (2019)
- [How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR](https://mlsanity.com/paper/2201.06685/) (2022)
- [Differentiable Consistency Constraints for Improved Deep Speech Enhancement](https://mlsanity.com/paper/1811.08521/) (2018)
- [The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios](https://mlsanity.com/paper/2306.13734/) (2023)
- [NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription](https://mlsanity.com/paper/2401.08887/) (2024)
- [Far-Field Automatic Speech Recognition](https://mlsanity.com/paper/2009.09395/) (2020)
- [Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation](https://mlsanity.com/paper/2010.01703/) (2020)
- [Summary On The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge](https://mlsanity.com/paper/2202.03647/) (2022)
- [The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization](https://mlsanity.com/paper/2407.16447/) (2024)
- [VarArray: Array-Geometry-Agnostic Continuous Speech Separation](https://mlsanity.com/paper/2110.05745/) (2021)
- [Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation](https://mlsanity.com/paper/2108.07376/) (2021)
- [Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions](https://mlsanity.com/paper/2110.14139/) (2021)
- [The Multimodal Information based Speech Processing (MISP) 2022 Challenge: Audio-Visual Diarization and Recognition](https://mlsanity.com/paper/2303.06326/) (2023)
- [VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition](https://mlsanity.com/paper/2209.04974/) (2022)
- [Adapting Speech Separation to Real-World Meetings Using Mixture Invariant Training](https://mlsanity.com/paper/2110.10739/) (2021)
- [Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation](https://mlsanity.com/paper/2106.07843/) (2021)
- [The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge](https://mlsanity.com/paper/2308.14638/) (2023)

## Abstract (arXiv)

In conversational speech separation and recognition tasks, close-talk microphones are typically attached to each speaker during training data collection to capture near-field, close-talk mixture signals, in addition to using far-field microphones to record far-field mixture signals. Each such close-talk mixture exhibits a reasonably high energy level for the wearer and could intuitively serve as weak supervision for training far-field speech separation models directly on real-recorded far-field signals. However, they are not sufficiently clean for this purpose, as they often contain strong cross-talk speech from other speakers in addition to background noise. To address this, we propose cross-talk reduction (CTR), a task aiming to isolate the wearer's speech from each close-talk mixture, and a novel method called CTRnet, which can be trained directly on real-recorded pairs of close-talk and far-field mixtures to accomplish CTR. Building on CTRnet, we further propose pseudo-label based far-field speech separation (PuLSS), which uses CTRnet's estimated clean speech as pseudo-labels to train models for separating far-field mixtures. A key advantage of the proposed framework is that both CTRnet and PuLSS can be trained on real-recorded data from the target domain, addressing the generalization gap commonly observed when models are trained exclusively on simulated data. On the CHiME-6 dataset, our framework achieves state-of-the-art ASR performance under both oracle and estimated speaker diarization, surpassing all CHiME-{7,8} challenge submissions. To our knowledge, it is the first neural speech separation method that substantially outperforms guided source separation on real conversational "speech-in-the-wild" data.