# NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection

arXiv: https://arxiv.org/abs/2312.07513 · HTML: https://mlsanity.com/paper/2312.07513/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2023.

## Built on by (most cited first, 6 of 6)

- [AAD-LLM: Neural Attention-Driven Auditory Scene Understanding](https://mlsanity.com/paper/2502.16794/) (2025)
- [Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction](https://mlsanity.com/paper/2505.20635/) (2025)
- [NeuroSpex: Neuro-Guided Speaker Extraction with Cross-Modal Attention](https://mlsanity.com/paper/2409.02489/) (2024)
- [Brainprint-Modulated Target Speaker Extraction](https://mlsanity.com/paper/2509.17883/) (2025)
- [Breaking Shortcut Learning for Cross-Trial EEG-Guided Target Speech Extraction via Two-Stage Training](https://mlsanity.com/paper/2606.24164/) (2026)
- [MAESTRO: a Multimodal Auditory-attention Egocentric Speech-TRacking Open corpus](https://mlsanity.com/paper/2609.31898/) (2026)

## Abstract (arXiv)

Neuro-steered speaker extraction aims to extract the listener's brain-attended speech signal from a multi-talker speech signal, in which the attention is derived from the cortical activity. This activity is usually recorded using electroencephalography (EEG) devices. Though promising, current methods often have a high speaker confusion error, where the interfering speaker is extracted instead of the attended speaker, degrading the listening experience. In this work, we aim to reduce the speaker confusion error in the neuro-steered speaker extraction model through a jointly fine-tuned auxiliary auditory attention detection model. The latter reinforces the consistency between the extracted target speech signal and the EEG representation, and also improves the EEG representation. Experimental results show that the proposed network significantly outperforms the baseline in terms of speaker confusion and overall signal quality in two-talker scenarios.