Paper Citation Record · LEDGER

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries

As of 20 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2507.12723.

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

pith.paper-citation-record.v1
2507.12723 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:45:54.536804Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:45:49.818821Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T16:45:54.946643Z

Reference resolution

41 of 41 outbound references displayed

verified exact2
verified fuzzy26
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a25f8065-3a17-4cef-a89b-32277d43078f · outbound

This paper cites an unresolved cited work.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:46:00.234428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 25c12320-9ae1-42b1-82a1-810bb793b25c · outbound

This paper cites Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:45:55.025578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d6619807-2e32-46e3-baed-cd826fddd4c1 · outbound

This paper cites an unresolved cited work.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:46:00.104538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a3f5f2fb-ceaf-4fe4-9090-1bafd1e75d36 · outbound

This paper cites Semantic Feature Contrastive LossTo ensure robust tam- per localization, we compare the tampered and recovered audio streams in a semantic feature space.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Semantic Feature Contrastive LossTo ensure robust tam- per localization, we compare the tampered and recovered audio streams in a semantic feature space

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:59.913070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ec97d494-547a-4834-8835-68a045094ef1 · outbound

This paper cites No Mask” refers to training without a mask. Our masking strategies outperform “No Mask.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries No Mask” refers to training without a mask. Our masking strategies outperform “No Mask

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:59.766837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f0e59333-d118-47a3-a28f-f69472846bb2 · outbound

This paper cites To achieve this, we propose cross-modal watermarking method not only localizing tampered regions but also recover- ing authentic audio.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries To achieve this, we propose cross-modal watermarking method not only localizing tampered regions but also recover- ing authentic audio

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:59.598713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 73223795-f2e0-4ca2-9208-39d41d1c7d46 · outbound

This paper cites an unresolved cited work.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:45:59.401149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cc92fce9-8588-4000-81ec-b2f8b062ca31 · outbound

This paper cites V oice- box: Text-guided multilingual universal speech generation at scale,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries V oice- box: Text-guided multilingual universal speech generation at scale,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:59.214657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 71f584fe-cfd8-42c9-965f-2992f64d5566 · outbound

This paper cites Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:59.049190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0b4fa284-f4ef-4059-a7e3-cfe7be6d70e6 · outbound

This paper cites Prompttts++: Controlling speaker identity in prompt-based text-to-speech using natural lan- guage descriptions,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Prompttts++: Controlling speaker identity in prompt-based text-to-speech using natural lan- guage descriptions,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:58.870054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b89aa9a3-7056-4595-8637-97608f5fe06a · outbound

This paper cites OpenVoice: Versatile Instant Voice Cloning.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries OpenVoice: Versatile Instant Voice Cloning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:50.581929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81502a34-be0a-47c3-9da7-091f66d9bc2e · outbound

This paper cites Paddlespeech: An easy-to-use all-in-one speech toolkit,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Paddlespeech: An easy-to-use all-in-one speech toolkit,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:58.712099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3aba5e75-4eea-4ad4-9ecf-3adae756963e · outbound

This paper cites Voice Cloning: a Multi-Speaker Text-to-Speech Synthesis Approach based on Transfer Learning.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Voice Cloning: a Multi-Speaker Text-to-Speech Synthesis Approach based on Transfer Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:50.765524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 229c49e3-fa14-4f9c-bb0f-38942db4d6a1 · outbound

This paper cites A lip sync expert is all you need for speech to lip generation in the wild,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries A lip sync expert is all you need for speech to lip generation in the wild,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:50.866421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5d8182c-2d28-4ac4-b4b0-136a5d140498 · outbound

This paper cites Diff2lip: Audio conditioned diffusion models for lip- synchronization,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Diff2lip: Audio conditioned diffusion models for lip- synchronization,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:58.518164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 53301581-388c-4586-a1e1-8555189d3b96 · outbound

This paper cites Pose-controllable talking face generation by implicitly modular- ized audio-visual representation,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Pose-controllable talking face generation by implicitly modular- ized audio-visual representation,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:58.303254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 98f9c78d-94b4-4d71-bb5e-9f17137ba254 · outbound

This paper cites TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:45:54.731731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b077b6a2-bf19-4acd-922f-2bf55b3c6242 · outbound

This paper cites Synctalklip: Highly synchronized lip-readable speaker generation with multi-task learning,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Synctalklip: Highly synchronized lip-readable speaker generation with multi-task learning,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:58.113236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b5bf171c-b948-419b-8bfc-8ca4c4a494a6 · outbound

This paper cites Editguard: Versatile image watermarking for tamper localization and copy- right protection,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Editguard: Versatile image watermarking for tamper localization and copy- right protection,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:57.865630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 72669cce-d637-4d0e-b732-dca031e82883 · outbound

This paper cites Proactive detection of voice cloning with localized watermarking,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Proactive detection of voice cloning with localized watermarking,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:57.715993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1f2ba057-3157-4c10-ab2e-eab0e2af9c8d · outbound

This paper cites Enhancing Partially Spoofed Audio Localization with Boundary-aware Attention Mechanism.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Enhancing Partially Spoofed Audio Localization with Boundary-aware Attention Mechanism

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:51.888779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0080dac6-140f-43b4-b90a-2f0c27ad71ea · outbound

This paper cites Coarse- to-fine proposal refinement framework for audio temporal forgery detection and localization,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Coarse- to-fine proposal refinement framework for audio temporal forgery detection and localization,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:57.559506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c0570cfc-711b-4ea6-8770-abba5c953757 · outbound

This paper cites Wavmark: Watermarking for audio generation,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Wavmark: Watermarking for audio generation,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:57.343824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 615ad3a1-de66-4b32-943f-8f0fe7785935 · outbound

This paper cites Hiding data in images by simple lsb substitution,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Hiding data in images by simple lsb substitution,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:57.191686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c8440b55-d5a8-4687-a597-fddd9084fa02 · outbound

This paper cites Complete video quality-preserving data hiding,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Complete video quality-preserving data hiding,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:57.038920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b970d1cc-97a7-4998-b259-4e1814ea24cd · outbound

This paper cites SteganoGAN: High Capacity Image Steganography with GANs.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries SteganoGAN: High Capacity Image Steganography with GANs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:52.573245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67a01fa2-a2a6-4d05-9fcf-565b0113052e · outbound

This paper cites NICE: Non-linear Independent Components Estimation.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries NICE: Non-linear Independent Components Estimation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:52.709737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f153a800-45aa-4f98-a867-49995a956c3a · outbound

This paper cites Hinet: Deep image hiding by invertible network,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Hinet: Deep image hiding by invertible network,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:56.844075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5fb90bcc-4121-42f4-abb8-0613fea70645 · outbound

This paper cites Large-capacity and flexible video steganography via invertible neural network,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Large-capacity and flexible video steganography via invertible neural network,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:56.713613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 11ac612b-a30f-41e9-91da-3642659a8a73 · outbound

This paper cites Thinimg: Cross-modal steganography for presenting talking heads in images,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Thinimg: Cross-modal steganography for presenting talking heads in images,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:56.529900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 953805b2-14eb-4e8f-abaa-34a962a09c8e · outbound

This paper cites Densely connected convolutional networks,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Densely connected convolutional networks,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:56.342670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation afe04c73-1ffd-4c35-ac6d-8985cd75e0ca · outbound

This paper cites Cnn architectures for large-scale audio classification,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Cnn architectures for large-scale audio classification,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:56.157926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6d9353e5-e375-432a-b6f9-ec3483484898 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Representation Learning with Contrastive Predictive Coding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:53.537636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad9db548-882e-41dd-acb4-d7516b626039 · outbound

This paper cites Lightface: A hybrid deep face recognition framework,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Lightface: A hybrid deep face recognition framework,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:55.988215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2a2bd7e8-bdc5-4d37-beb6-66f7fe7deca1 · outbound

This paper cites Flow-guided one-shot talk- ing face generation with a high-resolution audio-visual dataset,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Flow-guided one-shot talk- ing face generation with a high-resolution audio-visual dataset,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:55.759725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 80ba801b-e27a-466a-b7de-f8c384c73ac8 · outbound

This paper cites LRS3-TED: a large-scale dataset for visual speech recognition.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries LRS3-TED: a large-scale dataset for visual speech recognition

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:53.924279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 097491e6-36c7-4393-9268-f2bb64e5a0a4 · outbound

This paper cites V2a- mark: Versatile deep visual-audio watermarking for manipulation localization and copyright protection,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries V2a- mark: Versatile deep visual-audio watermarking for manipulation localization and copyright protection,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:55.579282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8bb5e626-134a-475d-9179-74e5dfaa2c73 · outbound

This paper cites Musetalk: Real-time high quality lip synchorization with latent space inpainting,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Musetalk: Real-time high quality lip synchorization with latent space inpainting,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:55.436801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c93bb14d-866d-450a-aaea-3dc1355e87b4 · outbound

This paper cites Video enhancement with task-oriented flow,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Video enhancement with task-oriented flow,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:54.316832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dcdb2be-cec6-4c2c-b9ec-e1ce30e325c3 · outbound

This paper cites FMA: A dataset for music analysis,.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries FMA: A dataset for music analysis,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:45:55.220089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4fee4e4e-2041-4248-86d3-983a29494207 · outbound

This paper cites FMA: A Dataset For Music Analysis.

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries FMA: A Dataset For Music Analysis

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:54.536804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 25c12320-9ae1-42b1-82a1-810bb793b25c · inbound