RoSS: Utilizing Robotic Rotation for Audio Source Separation

TL;DR

This paper introduces RoSS, a robotic rotation-based method for audio source separation that leverages microphone movement to improve separation quality, demonstrated on a functional prototype for robotic and device applications.

Contribution

The paper presents a novel approach using robotic rotation to enhance audio source separation, addressing mobility challenges and demonstrating practical effectiveness.

Findings

Rotating microphones can merge interferers, reducing sources by one.

The approach improves separation performance in real-world robotic setups.

RoSS can be integrated into robotic heads and rotating devices.

Abstract

This paper considers the problem of audio source separation where the goal is to isolate a target audio signal (say Alice's speech) from a mixture of multiple interfering signals (e.g., when many people are talking). This problem has gained renewed interest mainly due to the significant growth in voice controlled devices, including robots in homes, offices, and other public facilities. Although a rich body of work exists on the core topic of source separation, we find that robotic motion of the microphone -- say the robot's head -- is a complementary opportunity to past approaches. Briefly, we show that rotating the microphone array to the correct orientation can produce desired aliasing between two interferers, causing the two interferers to pose as one. In other words, a mixture of K signals becomes a mixture of (K-1), a mathematically concrete gain. We show that the gain translates well to practice provided two mobility-related challenges can be mitigated. This paper is focused on mitigating these challenges and demonstrating the end-to-end performance on a fully functional prototype. We believe that our Rotational Source Separation module RoSS could be plugged into actual robot heads, or into other devices (like Amazon Show) that are also capable of rotation.