Paper Citation Record · LEDGER

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations

As of 9 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 2 inbound Pith citation observations for arXiv:2507.21448.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2507.21448 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T12:50:00.951657Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T12:50:00.733134Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-01T14:25:47.176963Z

Reference resolution

41 of 41 outbound references displayed

verified exact2
verified fuzzy34
unresolved5
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d106859a-c6e3-4b29-85e9-e2332ce048a8 · outbound

This paper cites an unresolved cited work.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:50:08.154237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 28cb8503-5e9d-4c82-9740-8c72d3551bec · outbound

This paper cites Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T12:50:00.733134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9ee473f-0af7-45fd-a927-7e9eec61fc6a · outbound

This paper cites Datasets We use V oxCeleb2 as the speech dataset and MUSAN for noise and music.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Datasets We use V oxCeleb2 as the speech dataset and MUSAN for noise and music

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:07.885831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fe688ff9-3a4b-415d-ad9d-7da2dd460b0b · outbound

This paper cites an unresolved cited work.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-06T12:50:07.587783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 043a9f23-38cb-400b-b8aa-b8a7632bcb31 · outbound

This paper cites We systemat- ically analyze how visual embeddings from audio-visual speech recognition (A VSR) and active speaker detection (ASD) im- pact A VSE performance.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations We systemat- ically analyze how visual embeddings from audio-visual speech recognition (A VSR) and active speaker detection (ASD) im- pact A VSE performance

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:07.283456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8cc567b3-95f6-49d6-affb-f61ab3fbe687 · outbound

This paper cites Funda- mentals, present and future perspectives of speech enhancement,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Funda- mentals, present and future perspectives of speech enhancement,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:06.957541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6603e162-ab9a-48c5-87de-ad0fe3314878 · outbound

This paper cites An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:06.644010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a2b8f46e-57a4-4bc8-b7c1-2d3e777d5d76 · outbound

This paper cites FlowA VSE: Effi- cient Audio-Visual Speech Enhancement with Conditional Flow Matching,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations FlowA VSE: Effi- cient Audio-Visual Speech Enhancement with Conditional Flow Matching,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:06.324806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f16c5e63-8812-4029-b90c-e8327b680cd1 · outbound

This paper cites Personalized speech enhancement: new models and Comprehensive evaluation,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Personalized speech enhancement: new models and Comprehensive evaluation,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:06.109228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ec41fe69-5a12-4ac1-9fa3-8f61a6135da1 · outbound

This paper cites Real-Time Audio-Visual End-to-End Speech Enhancement,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Real-Time Audio-Visual End-to-End Speech Enhancement,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:05.905454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 93e19642-7f0d-45c4-b5c1-82a5c30dd41d · outbound

This paper cites Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:05.752116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 41dcc2f1-e283-4f1b-bfaf-dba2194b384e · outbound

This paper cites The Conversation: Deep Audio-Visual Speech Enhancement,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations The Conversation: Deep Audio-Visual Speech Enhancement,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:05.546179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 71d3d07a-a00f-4cdc-ad8b-52e049c05e8c · outbound

This paper cites Improved Lite Audio- Visual Speech Enhancement,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Improved Lite Audio- Visual Speech Enhancement,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:05.219113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6d7ade20-feb2-4ca5-a041-e58855dbae5b · outbound

This paper cites Lite Audio- Visual Speech Enhancement,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Lite Audio- Visual Speech Enhancement,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:04.981991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 36ccab49-88be-4571-84f6-0b66294fdd9f · outbound

This paper cites End-to-end Audio-visual Speech Recognition with Conformers,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations End-to-end Audio-visual Speech Recognition with Conformers,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:04.721415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ff992ea9-cec4-4d7a-8524-b16de94de606 · outbound

This paper cites Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:04.471416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 58298bd1-13a6-4b4c-8c64-1303f715c0a7 · outbound

This paper cites A Novel Real-Time, Lightweight Chaotic-Encryption Scheme for Next- Generation Audio-Visual Hearing Aids,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations A Novel Real-Time, Lightweight Chaotic-Encryption Scheme for Next- Generation Audio-Visual Hearing Aids,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:04.286004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bfb62780-2c0f-496b-9138-d95029e2e822 · outbound

This paper cites Lip- Reading Driven Deep Learning Approach for Speech Enhance- ment,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Lip- Reading Driven Deep Learning Approach for Speech Enhance- ment,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:04.040336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 456aca05-6cfe-4c8c-b3f7-9887d564587c · outbound

This paper cites Audio-visual speech enhancement using deep neural networks,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Audio-visual speech enhancement using deep neural networks,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:03.809284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation efe08a43-f7f2-46c9-977a-4fb752add33f · outbound

This paper cites Audio-Visual Scene Analysis with Self-Supervised Multisensory Features,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Audio-Visual Scene Analysis with Self-Supervised Multisensory Features,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:03.656679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a7608f3b-cb83-422c-a4a2-ef088fc628f1 · outbound

This paper cites Evaluating Audiovisual Source Separation in the Context of Video Conferencing,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Evaluating Audiovisual Source Separation in the Context of Video Conferencing,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:03.495437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bb2528b1-7047-4d06-95f7-4707018a963d · outbound

This paper cites CochleaNet: A robust language-independent audio-visual model for real-time speech enhancement,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations CochleaNet: A robust language-independent audio-visual model for real-time speech enhancement,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:03.283326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dbbd2a9a-9b4c-4af3-b48e-b3414632f914 · outbound

This paper cites RT-LA-V ocE: Real- Time Low-SNR Audio-Visual Speech Enhancement,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations RT-LA-V ocE: Real- Time Low-SNR Audio-Visual Speech Enhancement,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:03.110631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f9666af7-49c0-4b77-9739-43f790274900 · outbound

This paper cites Exploring Tradeoffs in Models for Low-Latency Speech Enhancement,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Exploring Tradeoffs in Models for Low-Latency Speech Enhancement,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:02.900687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 461f0d2d-4cb5-4788-ab00-c1ca4ef1c00a · outbound

This paper cites Phase- sensitive and recognition-boosted speech separation using deep recurrent neural networks,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Phase- sensitive and recognition-boosted speech separation using deep recurrent neural networks,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:02.659182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b1b86e74-3ec7-4364-90d5-71c309b90f24 · outbound

This paper cites On The Compensation Between Magnitude and Phase in Speech Separation.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations On The Compensation Between Magnitude and Phase in Speech Separation

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-06T12:50:01.119128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 35634989-c821-4f5d-9702-041a675255ac · outbound

This paper cites Learn- ing Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Learn- ing Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:02.452880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4be04175-9aba-4d25-8bb7-4c1f9d31a392 · outbound

This paper cites Robust Self-Supervised Audio-Visual Speech Recognition,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Robust Self-Supervised Audio-Visual Speech Recognition,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:02.254963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c83f124f-531d-47be-bf7d-6ed43c7bc8ae · outbound

This paper cites Visual Speech Recognition for Multiple Languages in the Wild.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Visual Speech Recognition for Multiple Languages in the Wild

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-06T12:50:01.052996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a4299ee8-9644-4ef2-b76c-783a57c86573 · outbound

This paper cites Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T12:50:00.887904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e8efe7a-2f6a-453d-bc3b-1a8a4c1d2a22 · outbound

This paper cites LoCoNet: Long-Short Context Network for Active Speaker Detection,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations LoCoNet: Long-Short Context Network for Active Speaker Detection,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:02.049957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 623afb87-27a1-420f-b9e9-92d3d3dd2098 · outbound

This paper cites Deep Contextualized Word Representa- tions,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Deep Contextualized Word Representa- tions,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:01.878281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7ad79254-0c6a-4a76-add1-0af98ccf5185 · outbound

This paper cites Few- shot Image Classification: Just Use a Library of Pre-trained Fea- ture Extractors and a Simple Classifier,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Few- shot Image Classification: Just Use a Library of Pre-trained Fea- ture Extractors and a Simple Classifier,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:01.651568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6cdf9559-167c-4aa0-9035-ae8f6ba41f81 · outbound

This paper cites Music auto-tagging in the long tail: A few-shot approach,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Music auto-tagging in the long tail: A few-shot approach,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:01.472179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7521eefd-a268-4a34-a654-eadff6bd0025 · outbound

This paper cites Contextual String Em- beddings for Sequence Labeling,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Contextual String Em- beddings for Sequence Labeling,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:01.398614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 736da3cf-bdca-444d-8d34-8482e8162dea · outbound

This paper cites DeepFilterNet: A Low Complexity Speech Enhancement Frame- work for Full-Band Audio based on Deep Filtering,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations DeepFilterNet: A Low Complexity Speech Enhancement Frame- work for Full-Band Audio based on Deep Filtering,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:01.362977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9a77b55c-e7fc-4f21-b061-7bf99b65d384 · outbound

This paper cites Perceptual eval- uation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations Perceptual eval- uation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:01.319553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 791b7492-0965-4f57-8f69-f1fd60cf026d · outbound

This paper cites SDR – Half-baked or Well Done?.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations SDR – Half-baked or Well Done?

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:01.278688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cec44eee-4d81-4e17-a0fe-17ad826ce9d1 · outbound

This paper cites An Algorithm for Predicting the In- telligibility of Speech Masked by Modulated Noise Maskers,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations An Algorithm for Predicting the In- telligibility of Speech Masked by Modulated Noise Maskers,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T12:50:00.938902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 587209d4-2447-4d2d-ab72-2a0335df526d · outbound

This paper cites ViSpeR: Multilingual Audio-Visual Speech Recognition,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations ViSpeR: Multilingual Audio-Visual Speech Recognition,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:01.224069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4c3a8019-162a-48d6-b28a-553cc93946d2 · outbound

This paper cites MEAD: A Large-Scale Audio-Visual Dataset for Emotional Talking-Face Generation,.

Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations MEAD: A Large-Scale Audio-Visual Dataset for Emotional Talking-Face Generation,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T12:50:01.187419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation 28cb8503-5e9d-4c82-9740-8c72d3551bec · inbound