mlsanityData to 19 Oct 2026

Mixture to Beamformed Mixture: Leveraging Beamformed Mixture as Weak-Supervision for Speech Enhancement and Noise-Robust ASR

arXiv 2507.15229 ↗First posted 21 Jul 2025eess.AScited by 0

On the map: Speech and audio language models → Speech enhancement and noise suppression

Abstract (arXiv)

In multi-channel speech enhancement and robust automatic speech recognition (ASR), beamforming can typically improve the signal-to-noise ratio (SNR) of the target speaker and produce reliable enhancement with little distortion to target speech. With this observation, we propose to leverage beamformed mixture, which has a higher SNR of the target speaker than the input mixture, as a weak supervision to train deep neural networks (DNNs) to enhance the input mixture. This way, we can train enhancement models using pairs of real-recorded mixture and its beamformed mixture, and potentially realize better generalization to real mixtures, compared with only training the models on simulated mixtures, which usually mismatch real mixtures. Evaluation results on the real-recorded CHiME-4 dataset show the effectiveness of the proposed algorithm.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models. Builds on 31 of its 46 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

31 of 46 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Microphone Array Signal Processing and Deep Learning for Speech Enhancement13 Jan
  2. 2024SuperM2M: Supervised and Mixture-to-Mixture Co-Learning for Speech Enhancement and Noise-Robust ASR15 Mar
  3. 2024Improving Design of Input Condition Invariant Speech Enhancement25 Jan
  4. 2023Toward Universal Speech Enhancement for Diverse Input Conditions29 Sep
  5. 2022End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation1 Apr
  6. 2022RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing17 Feb
  7. 2021Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech21 Jan

Other references · 24

  1. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 2,135
  2. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 356
  3. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 342
  4. 2020CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordingscited by 231
  5. 2021M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challengecited by 149
  6. 2022TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separationcited by 121
  7. 2019MIMO-SPEECH: End-to-End Multi-Channel Multi-Speaker Speech Recognitioncited by 67
  8. 2020Far-Field Automatic Speech Recognitioncited by 50
  9. 2021Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separationcited by 21
  10. 2019Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervisioncited by 18
  11. 2022End-to-End Integration of Speech Recognition, Dereverberation, Beamforming, and Self-Supervised Learning Representationcited by 18
  12. 2023The Multimodal Information based Speech Processing (MISP) 2022 Challenge: Audio-Visual Diarization and Recognitioncited by 18
12 more
  1. 2019Unsupervised training of a deep clustering model for multichannel blind source separationcited by 17
  2. 2018Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Informationcited by 15
  3. 2017Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extractioncited by 13
  4. 202530+ Years of Source Separation Research: Achievements and Future Challengescited by 11
  5. 2023UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixturescited by 10
  6. 2025ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Priorcited by 10
  7. 2024USDnet: Unsupervised Speech Dereverberation via Neural Forward Filteringcited by 9
  8. 2018Bootstrapping single-channel source separation via unsupervised spatial clustering on stereo mixturescited by 8
  9. 2023Overview Of The 2023 Icassp Sp Clarity Challenge: Speech Enhancement For Hearing Aidscited by 6
  10. 2024Mixture to Mixture: Leveraging Close-talk Mixtures as Weak-supervision for Speech Separationcited by 5
  11. 2025A Survey of Deep Learning for Complex Speech Spectrogramscited by 5
  12. 2022Reverberation as Supervision for Speech Separationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022TaylorBeamformer: Learning All-Neural Beamformer for Multi-Channel Speech Enhancement from Taylor's Approximation Theory
  2. 2022TaylorBeamixer: Learning Taylor-Inspired All-Neural Multi-Channel Speech Enhancement from Beam-Space Dictionary Perspective
  3. 2022A Neural Beam Filter for Real-time Multi-channel Speech Enhancement
  4. 2026UltraM2M: Leveraging Text Transcripts and Mixture Constraints for Weakly-Supervised Speech Enhancement
  5. 2024Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising
  6. 2021Multichannel Speech Enhancement without Beamforming
  7. 2022DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF
  8. 2025ARiSE: Auto-Regressive Multi-Channel Speech Enhancement