Leveraging Spatial Cues from Cochlear Implant Microphones to Efficiently Enhance Speech Separation in Real-World Listening Scenes

TL;DR

This paper investigates how spatial cues from cochlear implant microphones can be leveraged to improve speech separation in real-world environments, addressing challenges posed by reverberation and spatial ambiguity for assistive hearing devices.

Contribution

It introduces methods to utilize both implicit and explicit spatial cues to enhance speech separation performance in cochlear implant scenarios, especially in complex acoustic environments.

Findings

Spatial cues improve separation for spatially separated talkers

Explicit spatial cues benefit when implicit cues are weak

Training on real-world data enhances model generalizability

Abstract

Speech separation approaches for single-channel, dry speech mixtures have significantly improved. However, real-world spatial and reverberant acoustic environments remain challenging, limiting the effectiveness of these approaches for assistive hearing devices like cochlear implants (CIs). To address this, we quantify the impact of real-world acoustic scenes on speech separation and explore how spatial cues can enhance separation quality efficiently. We analyze performance based on implicit spatial cues (inherent in the acoustic input and learned by the model) and explicit spatial cues (manually calculated spatial features added as auxiliary inputs). Our findings show that spatial cues (both implicit and explicit) improve separation for mixtures with spatially separated and nearby talkers. Furthermore, spatial cues enhance separation when spectral cues are ambiguous, such as when voices are similar. Explicit spatial cues are particularly beneficial when implicit spatial cues are weak. For instance, single CI microphone recordings provide weaker implicit spatial cues than bilateral CIs, but even single CIs benefit from explicit cues. These results emphasize the importance of training models on real-world data to improve generalizability in everyday listening scenarios. Additionally, our statistical analyses offer insights into how data properties influence model performance, supporting the development of efficient speech separation approaches for CIs and other assistive devices in real-world settings.