English

Mic2Mic: Using Cycle-Consistent Generative Adversarial Networks to Overcome Microphone Variability in Speech Systems

Audio and Speech Processing 2020-03-30 v1 Machine Learning Sound Machine Learning

Abstract

Mobile and embedded devices are increasingly using microphones and audio-based computational models to infer user context. A major challenge in building systems that combine audio models with commodity microphones is to guarantee their accuracy and robustness in the real-world. Besides many environmental dynamics, a primary factor that impacts the robustness of audio models is microphone variability. In this work, we propose Mic2Mic -- a machine-learned system component -- which resides in the inference pipeline of audio models and at real-time reduces the variability in audio data caused by microphone-specific factors. Two key considerations for the design of Mic2Mic were: a) to decouple the problem of microphone variability from the audio task, and b) put a minimal burden on end-users to provide training data. With these in mind, we apply the principles of cycle-consistent generative adversarial networks (CycleGANs) to learn Mic2Mic using unlabeled and unpaired data collected from different microphones. Our experiments show that Mic2Mic can recover between 66% to 89% of the accuracy lost due to microphone variability for two common audio tasks.

Keywords

Cite

@article{arxiv.2003.12425,
  title  = {Mic2Mic: Using Cycle-Consistent Generative Adversarial Networks to Overcome Microphone Variability in Speech Systems},
  author = {Akhil Mathur and Anton Isopoussu and Fahim Kawsar and Nadia Berthouze and Nicholas D. Lane},
  journal= {arXiv preprint arXiv:2003.12425},
  year   = {2020}
}

Comments

Published at ACM IPSN 2019

R2 v1 2026-06-23T14:29:21.091Z