The reviewed record of science sign in
Pith

arxiv: 2106.07994 · v1 · pith:LRO4RCH2 · submitted 2021-06-15 · eess.AS · cs.SD

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:LRO4RCH2record.jsonopen to challenge →

classification eess.AS cs.SD
keywords multi-channelcompressionapproachbitrateopusspatialarrayautomatic
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.