# Binaural Angular Separation Network

arXiv: https://arxiv.org/abs/2401.08864 · HTML: https://mlsanity.com/paper/2401.08864/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 16 Jan 2024.

## Builds on (most cited first, 10 of 10)

- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [Streaming keyword spotting on mobile devices](https://mlsanity.com/paper/2005.06720/) (2020)
- [FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing](https://mlsanity.com/paper/1909.13387/) (2019)
- [Embedding and Beamforming: All-neural Causal Beamformer for Multichannel Speech Enhancement](https://mlsanity.com/paper/2109.00265/) (2021)
- [VarArray: Array-Geometry-Agnostic Continuous Speech Separation](https://mlsanity.com/paper/2110.05745/) (2021)
- [Distance-Based Sound Separation](https://mlsanity.com/paper/2207.00562/) (2022)
- [Location-based training for multi-channel talker-independent speaker separation](https://mlsanity.com/paper/2110.04289/) (2021)
- [Multi-Microphone Speaker Separation by Spatial Regions](https://mlsanity.com/paper/2303.07143/) (2023)
- [Guided Speech Enhancement Network](https://mlsanity.com/paper/2303.07486/) (2023)

## Built on by (most cited first, 1 of 1)

- [SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction](https://mlsanity.com/paper/2506.00273/) (2025)

## Abstract (arXiv)

We propose a neural network model that can separate target speech sources from interfering sources at different angular regions using two microphones. The model is trained with simulated room impulse responses (RIRs) using omni-directional microphones without needing to collect real RIRs. By relying on specific angular regions and multiple room simulations, the model utilizes consistent time difference of arrival (TDOA) cues, or what we call delay contrast, to separate target and interference sources while remaining robust in various reverberation environments. We demonstrate the model is not only generalizable to a commercially available device with a slightly different microphone geometry, but also outperforms our previous work which uses one additional microphone on the same device. The model runs in real-time on-device and is suitable for low-latency streaming applications such as telephony and video conferencing.