Low-Complexity Own Voice Reconstruction for Hearables with an In-Ear Microphone
arXiv:2409.04136 · doi:10.1109/ICASSP49660.2025.10887874
Abstract
Hearable devices, equipped with one or more microphones, are commonly used for speech communication. Here, we consider the scenario where a hearable is used to capture the user's own voice in a noisy environment. In this scenario, own voice reconstruction (OVR) is essential for enhancing the quality and intelligibility of the recorded noisy own voice signals. In previous work, we developed a deep learning-based OVR system, aiming to reduce the amount of device-specific recordings for training by using data augmentation with phoneme-dependent models of own voice transfer characteristics. Given the limited computational resources available on hearables, in this paper we propose low-complexity variants of an OVR system based on the FT-JNF architecture and investigate the required amount of device-specific recordings for effective data augmentation and fine-tuning. Simulation results show that the proposed OVR system considerably improves speech quality, even under constraints of low complexity and a limited amount of device-specific recordings.
5 pages, 3 figures, submitted to ICASSP 2025; typos corrected
References in corpus (7)
- Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancement
- Time-Domain Multi-modal Bone/air Conducted Speech Enhancement
- Configurable EBEN: Extreme Bandwidth Extension Network to enhance body-conducted speech capture
- Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement
- Training Strategies for Own Voice Reconstruction in Hearing Protection Devices using an In-ear Microphone
- Modeling of Speech-dependent Own Voice Transfer Characteristics for Hearables with In-ear Microphones
- Multi-Microphone Noise Data Augmentation for DNN-based Own Voice Reconstruction for Hearables in Noisy Environments