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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Olalere, Feyisayo, van der Heijden, Kiki, Stronks, Christiaan H., Briaire, Jeroen, Frijns, Johan HM, van Gerven, Marcel
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929685937520640
author Olalere, Feyisayo
van der Heijden, Kiki
Stronks, Christiaan H.
Briaire, Jeroen
Frijns, Johan HM
van Gerven, Marcel
author_facet Olalere, Feyisayo
van der Heijden, Kiki
Stronks, Christiaan H.
Briaire, Jeroen
Frijns, Johan HM
van Gerven, Marcel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14610
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Spatial Cues from Cochlear Implant Microphones to Efficiently Enhance Speech Separation in Real-World Listening Scenes
Olalere, Feyisayo
van der Heijden, Kiki
Stronks, Christiaan H.
Briaire, Jeroen
Frijns, Johan HM
van Gerven, Marcel
Sound
Artificial Intelligence
Audio and Speech Processing
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.
title Leveraging Spatial Cues from Cochlear Implant Microphones to Efficiently Enhance Speech Separation in Real-World Listening Scenes
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2501.14610