Browse State-of-the-Art › Target Speaker Extraction
Target Speaker Extraction
20 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
Extract the dialogue content of the specified target in a multi-person dialogue.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
No dataset record in the archive lists this task.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 55 · with a code link: 20 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 55 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 55 of 55, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
10 Dec 2022 2 repositories listedIn this paper, we describe our improved implementation of GSS that leverages the power of modern GPU-based pipelines, including batched processing of frequencies and segments, to provide 300x speed-up over CPU-based…
-
31 May 2025 1 repository listed Syntology official (archive's flag): 30 ran · 30 ran (of which 23 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified (of 41 harvested samples) · 41 pointer-only (licence)Specifically, to eliminate the temporal inconsistency between EEG and speech modalities, the modal alignment module that uses a contrastive learning strategy is applied to align the temporal features of both modalities.
-
10 Apr 2025 1 repository listedTo the best of our knowledge, LauraTSE is the first single-task TSE model to leverage an auto-regressive decoder-only language model as the backbone.
-
5 Feb 2025 1 repository listedExperiments demonstrate that Metis can serve as a foundation model for unified speech generation: Metis outperforms state-of-the-art task-specific or multi-task systems across five speech generation tasks, including…
-
21 Oct 2024 1 repository listedIn this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue.
-
24 Sep 2024 1 repository listedThe proposed method is evaluated on multiple speech restoration tasks, including speech denoising, bandwidth extension, codec artifact removal, and target speaker extraction.
-
24 Sep 2024 1 repository listedTarget speaker extraction (TSE) focuses on isolating the speech of a specific target speaker from overlapped multi-talker speech, which is a typical setup in the cocktail party problem.
-
12 Sep 2024 1 repository listedWe propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models.
-
4 Sep 2024 1 repository listedTraditionally, this process has relied on extracting a speaker embedding from a reference speech, in which a speaker recognition model is required.
-
2 Sep 2024 1 repository listedOur experiments show that the use of a dual path transformer in the separator backbone along with proposed training paradigm improves the CNN baseline by 3.
-
17 Jun 2024 1 repository listedAdding visual cues to audio-based speech separation can improve separation performance.
-
29 Apr 2024 1 repository listedTo this end, we propose a novel selective auditory attention mechanism, which can suppress interference speakers and non-speech signals to avoid incorrect speaker extraction.
-
11 Oct 2023 1 repository listedWe demonstrate that textual descriptions alone can effectively serve as cues for extraction, thus addressing privacy concerns and reducing dependency on voiceprints.
-
29 Sep 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)This is the first time-frequency domain audio-visual speech separation method to outperform all contemporary time-domain counterparts.
-
31 Oct 2022 1 repository listedIn this paper, we study the audio-visual speaker extraction algorithms with intermittent visual cue.
-
31 Mar 2022 1 repository listedWe propose a hybrid continuity loss function for time-domain speaker extraction algorithms to settle the over-suppression problem.
-
21 Feb 2022 1 repository listedSpeaker extraction aims to extract the target speaker's voice from a multi-talker speech mixture given an auxiliary reference utterance.
-
14 Jun 2021 1 repository listedA speaker extraction algorithm seeks to extract the speech of a target speaker from a multi-talker speech mixture when given a cue that represents the target speaker, such as a pre-enrolled speech utterance, or an…
-
30 Mar 2021 1 repository listedInspired by the study on target speaker extraction, e. g., SpEx, we propose a unified speaker verification framework for both single- and multi-talker speech, that is able to pay selective auditory attention to the…
-
15 Oct 2020 1 repository listedSpeaker extraction algorithm relies on the speech sample from the target speaker as the reference point to focus its attention.
-
Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction11 Jun 2025 0 repositories listedAudio-visual target speaker extraction (AV-TSE) models primarily rely on target visual cues to isolate the target speaker's voice from others.
-
FlowTSE: Target Speaker Extraction with Flow Matching20 May 2025 0 repositories listedTarget speaker extraction (TSE) aims to isolate a specific speaker's speech from a mixture using speaker enrollment as a reference.
-
Listen to Extract: Onset-Prompted Target Speaker Extraction8 May 2025 0 repositories listedWe propose listen to extract (LExt), a highly-effective while extremely-simple algorithm for monaural target speaker extraction (TSE).
-
C²AV-TSE: Context and Confidence-aware Audio Visual Target Speaker Extraction1 Apr 2025 0 repositories listedAudio-Visual Target Speaker Extraction (AV-TSE) aims to mimic the human ability to enhance auditory perception using visual cues.
-
23 Feb 2025 0 repositories listed Syntology 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)Target speaker extraction focuses on isolating a specific speaker's voice from an audio mixture containing multiple speakers.
-
AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement26 Jan 2025 0 repositories listedWe introduce AnyEnhance, a unified generative model for voice enhancement that processes both speech and singing voices.
-
Universal Speaker Embedding Free Target Speaker Extraction and Personal Voice Activity Detection7 Jan 2025 0 repositories listedDetermining 'who spoke what and when' remains challenging in real-world applications.
-
MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues11 Dec 2024 0 repositories listedAudio-visual Target Speaker Extraction (AV-TSE) aims to isolate the speech of a specific target speaker from an audio mixture using time-synchronized visual cues.
-
STCON System for the CHiME-8 Challenge17 Oct 2024 0 repositories listedThis paper describes the STCON system for the CHiME-8 Challenge Task 1 (DASR) aimed at distant automatic speech transcription and diarization with multiple recording devices.
-
1 Oct 2024 0 repositories listedResearch on audio clue-based target speaker extraction (TSE) has focused on modeling mixtures and reference speech, achieving strong results in English due to abundant datasets.
-
Two-stage Framework for Robust Speech Emotion Recognition Using Target Speaker Extraction in Human Speech Noise Conditions29 Sep 2024 0 repositories listed
-
Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learning21 Jul 2024 0 repositories listed
-
SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling1 Jul 2024 0 repositories listed
-
Binaural Selective Attention Model for Target Speaker Extraction18 Jun 2024 0 repositories listed
-
Target Speaker Extraction with Curriculum Learning12 Jun 2024 0 repositories listed
-
Enhancing Real-World Active Speaker Detection with Multi-Modal Extraction Pre-Training1 Apr 2024 0 repositories listed
-
Target Speaker Extraction by Directly Exploiting Contextual Information in the Time-Frequency Domain27 Feb 2024 0 repositories listed
-
Listening to Multi-talker Conversations: Modular and End-to-end Perspectives14 Feb 2024 0 repositories listed
-
A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, and Extraction12 Oct 2023 0 repositories listed
-
Conditional Diffusion Model for Target Speaker Extraction7 Oct 2023 0 repositories listed
-
The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction15 Sep 2023 0 repositories listed
-
SpeechX: Neural Codec Language Model as a Versatile Speech Transformer14 Aug 2023 0 repositories listed
-
Beamformer-Guided Target Speaker Extraction15 Mar 2023 0 repositories listed
-
Multi-Channel Target Speaker Extraction with Refinement: The WavLab Submission to the Second Clarity Enhancement Challenge15 Feb 2023 0 repositories listed
-
Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddings16 Jan 2023 0 repositories listed
-
ExARN: self-attending RNN for target speaker extraction2 Dec 2022 0 repositories listed
-
Adapting self-supervised models to multi-talker speech recognition using speaker embeddings1 Nov 2022 0 repositories listed
-
Exploiting spatial information with the informed complex-valued spatial autoencoder for target speaker extraction27 Oct 2022 0 repositories listed
-
Semi-supervised Time Domain Target Speaker Extraction with Attention18 Jun 2022 0 repositories listed
-
Speaker-conditioning Single-channel Target Speaker Extraction using Conformer-based Architectures27 May 2022 0 repositories listed
-
Coarse-to-Fine Recursive Speech Separation for Unknown Number of Speakers30 Mar 2022 0 repositories listed
-
New Insights on Target Speaker Extraction1 Feb 2022 0 repositories listed
-
Speaker-conditioned Target Speaker Extraction based on Customized LSTM Cells9 Apr 2021 0 repositories listed
-
Multimodal Attention Fusion for Target Speaker Extraction2 Feb 2021 0 repositories listed
-
Multi-Talker MVDR Beamforming Based on Extended Complex Gaussian Mixture Model17 Oct 2019 0 repositories listed
Syntology lines on 3 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections