SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures
Not on the map. Why?
Abstract (arXiv)
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 30deg angular region. Additionally, the performance of our system based on only two microphones exceeds that of conventional 5-microphone arrays.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 86 references that are in the map. First posted on arXiv 15 Apr 2025.
Builds on
26 of 86 references.
References · 26
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
- 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 649
- 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 166
- 2017Pyroomacoustics: A Python package for audio room simulations and array processing algorithmscited by 132
- 2022TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separationcited by 63
- 2020Asteroid: the PyTorch-based audio source separation toolkit for researcherscited by 45
- 2020ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detectioncited by 26
- 2020The Cone of Silence: Speech Separation by Localizationcited by 21
- 2021SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detectioncited by 15
- 2023Device-Robust Acoustic Scene Classification via Impulse Response Augmentationcited by 11
- 2023Semantic Hearing: Programming Acoustic Scenes with Binaural Hearablescited by 11
14 more
- 2024Look Once to Hear: Target Speech Hearing with Noisy Examplescited by 11
- 2021Monaural source separation: From anechoic to reverberant environmentscited by 9
- 2021Hybrid Neural Networks for On-device Directional Hearingcited by 8
- 2022ClearBuds: Wireless Binaural Earbuds for Learning-Based Speech Enhancementcited by 7
- 2024All Neural Low-latency Directional Speech Extractioncited by 7
- 2017Reflection-Aware Sound Source Localizationcited by 5
- 2022Towards Unified All-Neural Beamforming for Time and Frequency Domain Speech Separationcited by 5
- 2018Deep Learning Based Speech Beamformingcited by 4
- 2020Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separationcited by 4
- 2023Multi-Microphone Speaker Separation by Spatial Regionscited by 4
- 2023EarCough: Enabling Continuous Subject Cough Event Detection on Hearablescited by 1
- 2023The Human Auditory System and Audiocited by 1
- 2024ToMoBrush: Exploring Dental Health Sensing using a Sonic Toothbrushcited by 1
- 2024DeWinder: Single-Channel Wind Noise Reduction using Ultrasound Sensingcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.