SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures
Preprint
Abstract
Imagine placing your smartphone on a table in a noisy restaurant and clearly capturing the voices of friends seated around you, or recording a lecturer's voice with clarity in a reverberant auditorium. We introduce SonicSieve, the first intelligent directional speech extraction system for smartphones using a bio-inspired acoustic microstructure. Our passive design embeds directional cues onto incoming speech without any additional electronics. It attaches to the in-line mic of low-cost wired earphones which can be attached to smartphones. We present an end-to-end neural network that processes the raw audio mixtures in real-time on mobile devices. Our results show that SonicSieve achieves a signal quality improvement of 5.0 dB when focusing on a 30{\deg} angular region. Additionally, the performance of our system based on only two microphones exceeds that of conventional 5-microphone arrays.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- Hearable devices with sound bubblesNature Electronics, 2024
- Acoustic metamaterials for sound absorption and insulation in buildingsBuilding and Environment, 2024
- A Review on Sound Source Localization SystemsArchives of Computational Methods in Engineering, 2022
- Deep neural network models of sound localization reveal how perception is adapted to real-world environmentsNature Human Behaviour, 2022
- Using smart speakers to contactlessly monitor heart rhythmsCommunications Biology, 2021
- A microstructure material design for low frequency sound absorptionApplied Acoustics, 2018
- Direction of Arrival Estimation and Localization of Multi-Speech Sources2018
- The Auditory System and Human Sound-Localization Behavior2016
- Performance evaluation of classification algorithms by k-fold and leave-one-out cross validationPattern Recognition, 2015
- Theory of a generalized Helmholtz resonatorJournal of Sound and Vibration, 1973