mlsanityData to 19 Oct 2026

Multi-channel Opus compression for far-field automatic speech recognition with a fixed bitrate budget

arXiv 2106.07994 ↗First posted 15 Jun 2021eess.AS cs.SDcited by 0

On the map: Speech and audio language models → Speaker recognition and diarization

Abstract (arXiv)

Automatic speech recognition (ASR) in the cloud allows the use of larger models and more powerful multi-channel signal processing front-ends compared to on-device processing. However, it also adds an inherent latency due to the transmission of the audio signal, especially when transmitting multiple channels of a microphone array. One way to reduce the network bandwidth requirements is client-side compression with a lossy codec such as Opus. However, this compression can have a detrimental effect especially on multi-channel ASR front-ends, due to the distortion and loss of spatial information introduced by the codec. In this publication, we propose an improved approach for the compression of microphone array signals based on Opus, using a modified joint channel coding approach and additionally introducing a multi-channel spatial decorrelating transform to reduce redundancy in the transmission. We illustrate the effect of the proposed approach on the spatial information retained in multi-channel signals after compression, and evaluate the performance on far-field ASR with a multi-channel beamforming front-end. We demonstrate that our approach can lead to a 37.5 % bitrate reduction or a 5.1 % relative word error rate reduction for a fixed bitrate budget in a seven channel setup.

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 7 of its 30 references that are in the map. First posted on arXiv 15 Jun 2021.

Builds on

7 of 30 references.

References · 7

  1. 2019SpecAugment on Large Scale Datasetscited by 78
  2. 2020Far-Field Automatic Speech Recognitioncited by 50
  3. 2018Toward domain-invariant speech recognition via large scale trainingcited by 45
  4. 2016High-Quality, Low-Delay Music Coding in the Opus Codeccited by 26
  5. 2019Multi-Geometry Spatial Acoustic Modeling for Distant Speech Recognitioncited by 9
  6. 2016A Full-Bandwidth Audio Codec With Low Complexity And Very Low Delaycited by 2
  7. 2020Multi-channel Acoustic Modeling using Mixed Bitrate OPUS Compressioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Data-independent Beamforming for End-to-end Multichannel Multi-speaker ASR
  2. 2021Do You Listen with One or Two Microphones? A Unified ASR Model for Single and Multi-Channel Audio
  3. 2023Automatic channel selection and spatial feature integration for multi-channel speech recognition across various array topologies
  4. 2026SpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone Arrays
  5. 2021Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-field Speech Recognition
  6. 2026Multi-channel multi-speaker transformer for speech recognition
  7. 2022Exploiting Single-Channel Speech for Multi-Channel End-to-End Speech Recognition: A Comparative Study
  8. 2024One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model