# Target Speaker Extraction by Directly Exploiting Contextual Information in the Time-Frequency Domain

arXiv: https://arxiv.org/abs/2402.17146 · HTML: https://mlsanity.com/paper/2402.17146/

## Key facts

- Cited by 11 papers in the map (data through 19 Oct 2026).
- First posted on arXiv 27 Feb 2024.

## Built on by (most cited first, 11 of 11)

- [SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline](https://mlsanity.com/paper/2505.19314/) (2025)
- [USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction](https://mlsanity.com/paper/2409.02615/) (2024)
- [SEF-PNet: Speaker Encoder-Free Personalized Speech Enhancement with Local and Global Contexts Aggregation](https://mlsanity.com/paper/2501.11274/) (2025)
- [Universal Speaker Embedding Free Target Speaker Extraction and Personal Voice Activity Detection](https://mlsanity.com/paper/2501.03612/) (2025)
- [Unified Architecture and Unsupervised Speech Disentanglement for Speaker Embedding-Free Enrollment in Personalized Speech Enhancement](https://mlsanity.com/paper/2505.12288/) (2025)
- [Lightweight speech enhancement guided target speech extraction in noisy multi-speaker scenarios](https://mlsanity.com/paper/2508.19583/) (2025)
- [TripleC Learning and Lightweight Speech Enhancement for Multi-Condition Target Speech Extraction](https://mlsanity.com/paper/2512.04945/) (2025)
- [Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models](https://mlsanity.com/paper/2601.06006/) (2026)
- [Enroll-on-Wakeup: A First Comparative Study of Target Speech Extraction for Seamless Interaction in Real Noisy Human-Machine Dialogue Scenarios](https://mlsanity.com/paper/2602.15519/) (2026)
- [Unified Target-Speaker ASR with Text and Enrollment Speech Cues](https://mlsanity.com/paper/2609.33853/) (2026)
- [CF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE Challenge](https://mlsanity.com/paper/2610.21773/) (2026)

## Abstract (arXiv)

In target speaker extraction, many studies rely on the speaker embedding which is obtained from an enrollment of the target speaker and employed as the guidance. However, solely using speaker embedding may not fully utilize the contextual information contained in the enrollment. In this paper, we directly exploit this contextual information in the time-frequency (T-F) domain. Specifically, the T-F representations of the enrollment and the mixed signal are interacted to compute the weighting matrices through an attention mechanism. These weighting matrices reflect the similarity among different frames of the T-F representations and are further employed to obtain the consistent T-F representations of the enrollment. These consistent representations are served as the guidance, allowing for better exploitation of the contextual information. Furthermore, the proposed method achieves the state-of-the-art performance on the benchmark dataset and shows its effectiveness in the complex scenarios.