Leveraging Spatial Cues from Cochlear Implant Microphones to Efficiently Enhance Speech Separation in Real-World Listening Scenes
This work addresses speech separation in noisy, reverberant settings for cochlear implant users, offering incremental improvements by leveraging spatial cues to enhance model performance.
The study tackled the challenge of speech separation in real-world acoustic environments for cochlear implants by quantifying the impact of spatial cues, finding that both implicit and explicit spatial cues improve separation quality, with explicit cues particularly beneficial in scenarios like single-microphone recordings where implicit cues are weak.
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.