Browse State-of-the-Art › Speech Extraction
Speech Extraction
10 papers with code · 1 benchmark · 3 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| WSJ0-2mix-extr (1 row) | SpEx+ (tied) | SpEx+: A Complete Time Domain Speaker Extraction Network | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each 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 instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” 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.
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
3 datasets whose archive record lists this task, ordered by the archive's paper count.
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: 48 · with a code link: 10 · where Syntology ran a sample: 1 (0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 48 tagged: 0 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 48 of 48, 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.
-
25 May 2025 1 repository listedOn the other hand, generative models for TSE lag in perceptual quality and intelligibility.
-
15 Jan 2025 1 repository listedTo train and evaluate our model, we introduce a new dataset TextrolMix with speech mixtures and natural language descriptions.
-
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.
-
10 May 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)We present the first enrollment interface where the wearer looks at the target speaker for a few seconds to capture a single, short, highly noisy, binaural example of the target speaker.
-
31 Jan 2023 1 repository listedHumans can listen to a target speaker even in challenging acoustic conditions that have noise, reverberation, and interfering speakers.
-
15 Aug 2022 1 repository listedOne of the factors causing such degradation may be intrinsic speaker variability, such as emotions, occurring commonly in realistic speech.
-
22 Jun 2022 1 repository listedEmploying deep neural networks (DNNs) to directly learn filters for multi-channel speech enhancement has potentially two key advantages over a traditional approach combining a linear spatial filter with an independent…
-
27 Dec 2021 1 repository listedParticularly, we find that the Mixture-Remix fine-tuning with DPCCN significantly outperforms the TD-SpeakerBeam for unsupervised cross-domain TSE, with around 3.
-
16 May 2020 1 repository listedExtracting the desired speech from a mixture is a meaningful and challenging task.
-
23 Jan 2020 1 repository listedFirst, we propose a time-domain implementation of SpeakerBeam similar to that proposed for a time-domain audio separation network (TasNet), which has achieved state-of-the-art performance for speech separation.
-
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.
-
Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction2 Jun 2025 0 repositories listedWe propose a novel approach that utilizes inter-speaker relative cues to distinguish target speakers and extract their voices from mixtures.
-
Single-Channel Target Speech Extraction Utilizing Distance and Room Clues20 May 2025 0 repositories listedThis paper aims to achieve single-channel target speech extraction (TSE) in enclosures utilizing distance clues and room information.
-
SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures15 Apr 2025 0 repositories listedImagine placing your smartphone on a table in a noisy restaurant and clearly capturing the voices of friends seated around you, or recording a lecturer's voice with clarity in a reverberant auditorium.
-
Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction11 Mar 2025 0 repositories listedIn this paper, we investigate a novel approach for Target Speech Extraction (TSE), which relies solely on textual context to extract the target speech.
-
Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR24 Jan 2025 0 repositories listedTarget speech extraction (TSE) isolates the speech of a specific speaker from a multi-talker overlapped speech mixture.
-
Distance Based Single-Channel Target Speech Extraction28 Dec 2024 0 repositories listedThis paper aims to achieve single-channel target speech extraction (TSE) in enclosures by solely utilizing distance information.
-
Investigation of Speaker Representation for Target-Speaker Speech Processing15 Oct 2024 0 repositories listedTarget-speaker speech processing (TS) tasks, such as target-speaker automatic speech recognition (TS-ASR), target speech extraction (TSE), and personal voice activity detection (p-VAD), are important for extracting…
-
Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction19 Apr 2024 0 repositories listedThe integration of visual cues has revitalized the performance of the target speech extraction task, elevating it to the forefront of the field.
-
Probing Self-supervised Learning Models with Target Speech Extraction17 Feb 2024 0 repositories listedLarge-scale pre-trained self-supervised learning (SSL) models have shown remarkable advancements in speech-related tasks.
-
Target Speech Extraction with Pre-trained Self-supervised Learning Models17 Feb 2024 0 repositories listedPre-trained self-supervised learning (SSL) models have achieved remarkable success in various speech tasks.
-
Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction16 Dec 2023 0 repositories listedSpeech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information.
-
Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction30 Oct 2023 0 repositories listedTarget speech extraction aims to extract, based on a given conditioning cue, a target speech signal that is corrupted by interfering sources, such as noise or competing speakers.
-
AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data25 Sep 2023 0 repositories listedRecently, the utilization of extensive open-sourced text data has significantly advanced the performance of text-based large language models (LLMs).
-
DDTSE: Discriminative Diffusion Model for Target Speech Extraction25 Sep 2023 0 repositories listedDiffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods.
-
Target Speech Extraction with Conditional Diffusion Model8 Aug 2023 0 repositories listedDiffusion model-based speech enhancement has received increased attention since it can generate very natural enhanced signals and generalizes well to unseen conditions.
-
Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction28 Jun 2023 0 repositories listedRecently, deep learning-based beamforming algorithms have shown promising performance in target speech extraction tasks.
-
Audio-Visual Speech Enhancement With Selective Off-Screen Speech Extraction10 Jun 2023 0 repositories listedThis paper describes an audio-visual speech enhancement (AV-SE) method that estimates from noisy input audio a mixture of the speech of the speaker appearing in an input video (on-screen target speech) and of a selected…
-
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data25 May 2023 0 repositories listedNeural transducer (RNNT)-based target-speaker speech recognition (TS-RNNT) directly transcribes a target speaker's voice from a multi-talker mixture.
-
X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion9 Mar 2023 0 repositories listedTarget speech extraction (TSE) systems are designed to extract target speech from a multi-talker mixture.
-
Quotations, Coreference Resolution, and Sentiment Annotations in Croatian News Articles: An Exploratory Study14 Dec 2022 0 repositories listed
-
Streaming Target-Speaker ASR with Neural Transducer9 Sep 2022 0 repositories listed
-
ConceptBeam: Concept Driven Target Speech Extraction25 Jul 2022 0 repositories listed
-
Dual-Path Cross-Modal Attention for better Audio-Visual Speech Extraction9 Jul 2022 0 repositories listed
-
Simultaneous Speech Extraction for Multiple Target Speakers under the Meeting Scenarios17 Jun 2022 0 repositories listed
-
Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations16 Jun 2022 0 repositories listed
-
Listen only to me! How well can target speech extraction handle false alarms?11 Apr 2022 0 repositories listed
-
Deep Learning-Based Joint Control of Acoustic Echo Cancellation, Beamforming and Postfiltering3 Mar 2022 0 repositories listed
-
Learning-based personal speech enhancement for teleconferencing by exploiting spatial-spectral features10 Dec 2021 0 repositories listed
-
Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification5 Nov 2021 0 repositories listed
-
All-neural beamformer for continuous speech separation13 Oct 2021 0 repositories listed
-
Improving Channel Decorrelation for Multi-Channel Target Speech Extraction6 Jun 2021 0 repositories listed
-
Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism7 Feb 2021 0 repositories listed
-
Speaker activity driven neural speech extraction14 Jan 2021 0 repositories listed
-
Speaker Separation Using Speaker Inventories and Estimated Speech20 Oct 2020 0 repositories listed
-
Attention-based scaling adaptation for target speech extraction19 Oct 2020 0 repositories listed
-
Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR4 Jun 2020 0 repositories listed
-
Algorithm for Independent Vector Extraction Based on Semi-Time-Variant Mixing Model22 Oct 2019 0 repositories listed
Syntology lines on 1 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