# All Neural Low-latency Directional Speech Extraction

arXiv: https://arxiv.org/abs/2407.04879 · HTML: https://mlsanity.com/paper/2407.04879/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2024.

## Built on by (most cited first, 7 of 7)

- [Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios](https://mlsanity.com/paper/2505.14517/) (2025)
- [Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Clues](https://mlsanity.com/paper/2409.12415/) (2024)
- [Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance](https://mlsanity.com/paper/2507.02791/) (2025)
- [Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios](https://mlsanity.com/paper/2601.12345/) (2026)
- [SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures](https://mlsanity.com/paper/2504.10793/) (2025)
- [Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers](https://mlsanity.com/paper/2603.23723/) (2026)
- [SoundCompass: Navigating Target Sound Extraction With Effective Directional Clue Integration In Complex Acoustic Scenes](https://mlsanity.com/paper/2509.18561/) (2025)

## Abstract (arXiv)

We introduce a novel all neural model for low-latency directional speech extraction. The model uses direction of arrival (DOA) embeddings from a predefined spatial grid, which are transformed and fused into a recurrent neural network based speech extraction model. This process enables the model to effectively extract speech from a specified DOA. Unlike previous methods that relied on hand-crafted directional features, the proposed model trains DOA embeddings from scratch using speech enhancement loss, making it suitable for low-latency scenarios. Additionally, it operates at a high frame rate, taking in DOA with each input frame, which brings in the capability of quickly adapting to changing scene in highly dynamic real-world scenarios. We provide extensive evaluation to demonstrate the model's efficacy in directional speech extraction, robustness to DOA mismatch, and its capability to quickly adapt to abrupt changes in DOA.