Privacy and Quality Improvements in Open Offices Using Multi-Device Speech Enhancement

Abstract

Teleconferencing has increased in popularity and often takes place around other people such as open offices. A particular problem of such environments is that multiple users can have independent conversations simultaneously, which leak into each others' devices. This poses problems of both privacy and quality. In this work, we introduce a multi-device, targeted speech separation network. We call this network IsoNet, as it isolates the dominant speech in a mixture of multiple speakers by generating a mask from interfering speakers. This mask is used to remove speech from other simultaneous conversations in the enhanced speech signal. The privacy improvement is measured by mutual information and the enhancement quality is evaluated with a MUSHRA test, PESQ, and SI-SNR. Our experiments show a statistically significant improvement with IsoNet from 27 to 75 in MUSHRA score and a decrease of mutual information of 60%. IsoNet improves privacy as sensitive speech content is effectively attenuated.