# Hybrid Neural Networks for On-device Directional Hearing

arXiv: https://arxiv.org/abs/2112.05893 · HTML: https://mlsanity.com/paper/2112.05893/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 52 references that are in the map.
- First posted on arXiv 11 Dec 2021.

## Builds on (most cited first, 25 of 25)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [TasNet: time-domain audio separation network for real-time, single-channel speech separation](https://mlsanity.com/paper/1711.00541/) (2017)
- [Music Source Separation in the Waveform Domain](https://mlsanity.com/paper/1911.13254/) (2019)
- [Benchmarking TPU, GPU, and CPU Platforms for Deep Learning](https://mlsanity.com/paper/1907.10701/) (2019)
- [Sudo rm -rf: Efficient Networks for Universal Audio Source Separation](https://mlsanity.com/paper/2007.06833/) (2020)
- [A scalable noisy speech dataset and online subjective test framework](https://mlsanity.com/paper/1909.08050/) (2019)
- [TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids](https://mlsanity.com/paper/2005.11138/) (2020)
- [End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation](https://mlsanity.com/paper/1910.14104/) (2019)
- [FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing](https://mlsanity.com/paper/1909.13387/) (2019)
- [The Cone of Silence: Speech Separation by Localization](https://mlsanity.com/paper/2010.06007/) (2020)
- [ADL-MVDR: All deep learning MVDR beamformer for target speech separation](https://mlsanity.com/paper/2008.06994/) (2020)
- [End-to-End Multi-Channel Speech Separation](https://mlsanity.com/paper/1905.06286/) (2019)
- [Real-time binaural speech separation with preserved spatial cues](https://mlsanity.com/paper/2002.06637/) (2020)
- [Neural Spatio-Temporal Beamformer for Target Speech Separation](https://mlsanity.com/paper/2005.03889/) (2020)
- [High Performance Depthwise and Pointwise Convolutions on Mobile Devices](https://mlsanity.com/paper/2001.02504/) (2020)
- [Deep Learning Based Speech Beamforming](https://mlsanity.com/paper/1802.05383/) (2018)
- [Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation](https://mlsanity.com/paper/2001.00391/) (2020)
- [Cracking the cocktail party problem by multi-beam deep attractor network](https://mlsanity.com/paper/1803.10924/) (2018)

## Built on by (most cited first, 8 of 8)

- [Real-Time Target Sound Extraction](https://mlsanity.com/paper/2211.02250/) (2022)
- [Semantic Hearing: Programming Acoustic Scenes with Binaural Hearables](https://mlsanity.com/paper/2311.00320/) (2023)
- [Look Once to Hear: Target Speech Hearing with Noisy Examples](https://mlsanity.com/paper/2405.06289/) (2024)
- [Target conversation extraction: Source separation using turn-taking dynamics](https://mlsanity.com/paper/2407.11277/) (2024)
- [Spatial Speech Translation: Translating Across Space With Binaural Hearables](https://mlsanity.com/paper/2504.18715/) (2025)
- [Neural Speech Extraction with Human Feedback](https://mlsanity.com/paper/2508.03041/) (2025)
- [SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures](https://mlsanity.com/paper/2504.10793/) (2025)
- [TF-MLPNet: Tiny Real-Time Neural Speech Separation](https://mlsanity.com/paper/2508.03047/) (2025)

## Abstract (arXiv)

On-device directional hearing requires audio source separation from a given direction while achieving stringent human-imperceptible latency requirements. While neural nets can achieve significantly better performance than traditional beamformers, all existing models fall short of supporting low-latency causal inference on computationally-constrained wearables. We present DeepBeam, a hybrid model that combines traditional beamformers with a custom lightweight neural net. The former reduces the computational burden of the latter and also improves its generalizability, while the latter is designed to further reduce the memory and computational overhead to enable real-time and low-latency operations. Our evaluation shows comparable performance to state-of-the-art causal inference models on synthetic data while achieving a 5x reduction of model size, 4x reduction of computation per second, 5x reduction in processing time and generalizing better to real hardware data. Further, our real-time hybrid model runs in 8 ms on mobile CPUs designed for low-power wearable devices and achieves an end-to-end latency of 17.5 ms.