Learning to Separate Voices by Spatial Regions

Zhongweiyang Xu, Romit Roy Choudhury

Research output: Contribution to journalConference articlepeer-review

Abstract

We consider the problem of audio voice separation for binaural applications, such as earphones and hearing aids. While today's neural networks perform remarkably well (separating 4+ sources with 2 microphones) they assume a known or fixed maximum number of sources, K. Moreover, today's models are trained in a supervised manner, using training data synthesized from generic sources, environments, and human head shapes. This paper intends to relax both these constraints at the expense of a slight alteration in the problem definition. We observe that, when a received mixture contains too many sources, it is still helpful to separate them by region, i.e., isolating signal mixtures from each conical sector around the user's head. This requires learning the fine-grained spatial properties of each region, including the signal distortions imposed by a person's head. We propose a two-stage self-supervised framework in which overheard voices from earphones are preprocessed to extract relatively clean personalized signals, which are then used to train a region-wise separation model. Results show promising performance, underscoring the importance of personalization over a generic supervised approach. (audio samples available at our project website). We believe this result could help real-world applications in selective hearing, noise cancellation, and audio augmented reality.

Original languageEnglish (US)
Pages (from-to)24539-24549
Number of pages11
JournalProceedings of Machine Learning Research
Volume162
StatePublished - 2022
Externally publishedYes
Event39th International Conference on Machine Learning, ICML 2022 - Baltimore, United States
Duration: Jul 17 2022Jul 23 2022

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Learning to Separate Voices by Spatial Regions'. Together they form a unique fingerprint.

Cite this