mlsanityData to 19 Oct 2026

Flexible Multichannel Speech Enhancement for Noise-Robust Frontend

arXiv 2406.04552 ↗First posted 6 Jun 2024eess.AScited by 3

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

Abstract (arXiv)

This paper proposes a flexible multichannel speech enhancement system with the main goal of improving robustness of automatic speech recognition (ASR) in noisy conditions. The proposed system combines a flexible neural mask estimator applicable to different channel counts and configurations and a multichannel filter with automatic reference selection. A transform-attend-concatenate layer is proposed to handle cross-channel information in the mask estimator, which is shown to be effective for arbitrary microphone configurations. The presented evaluation demonstrates the effectiveness of the flexible system for several seen and unseen compact array geometries, matching the performance of fixed configuration-specific systems. Furthermore, a significantly improved ASR performance is observed for configurations with randomly-placed microphones.

Key facts. Cited by 3 papers in the map (data through 19 Oct 2026). Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models. Builds on 19 of its 40 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

19 of 40 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR18 Jan
  2. 2021One model to enhance them all: array geometry agnostic multi-channel personalized speech enhancement20 Oct
  3. 2021DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement30 Jun

Other references · 16

  1. 2017Attention Is All You Needcited by 61,180
  2. 2017Squeeze-and-Excitation Networkscited by 4,881
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 2,293
  4. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,149
  5. 2017Pyroomacoustics: A Python package for audio room simulations and array processing algorithmscited by 175
  6. 2022ICASSP 2022 Deep Noise Suppression Challengecited by 107
  7. 2019End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separationcited by 70
  8. 2020End-to-End Multi-speaker Speech Recognition with Transformercited by 58
  9. 2023Neural Target Speech Extraction: An Overviewcited by 52
  10. 2020Far-Field Automatic Speech Recognitioncited by 50
  11. 2018Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networkscited by 31
  12. 2021VarArray: Array-Geometry-Agnostic Continuous Speech Separationcited by 24
4 more
  1. 2020Neural Speech Separation Using Spatially Distributed Microphonescited by 15
  2. 2020Convolutive Transfer Function Invariant SDR training criteria for Multi-Channel Reverberant Speech Separationcited by 14
  3. 2022Mask-based Neural Beamforming for Moving Speakers with Self-Attention-based Trackingcited by 9
  4. 2020Scene-Agnostic Multi-Microphone Speech Dereverberationcited by 2

Built on by

Cited by year (2026 to 19 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025AmbiDrop: Array-Agnostic Speech Enhancement Using Ambisonics Encoding and Dropout-Based Learningcited by 2
  2. 2025Robust Speech Recognition with Schr"odinger Bridge-Based Speech Enhancementcited by 1
  3. 2026AmbiDrop: Ambisonics-Based Array-Agnostic Neural Speech Enhancementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Cleanformer: A multichannel array configuration-invariant neural enhancement frontend for ASR in smart speakers
  2. 2025Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning
  3. 2022Mask scalar prediction for improving robust automatic speech recognition
  4. 2024Reference Channel Selection by Multi-Channel Masking for End-to-End Multi-Channel Speech Enhancement
  5. 2022Time-Domain Speech Enhancement for Robust Automatic Speech Recognition
  6. 2021A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation
  7. 2025Spatial-Filter-Bank-Based Neural Method for Multichannel Speech Enhancement
  8. 2021An Investigation of End-to-End Models for Robust Speech Recognition