Paper Citation Record · LEDGER

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents

As of 19 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 3 inbound Pith citation observations for arXiv:2505.21568.

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

pith.paper-citation-record.v1
2505.21568 v2

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:52:46.527011Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:52:43.353115Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T12:29:52.013717Z

Reference resolution

31 of 31 outbound references displayed

verified exact1
verified fuzzy14
unresolved15
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ea8d6b6c-5020-4ef9-b1f5-c9b285b97071 · outbound

This paper cites VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:43.353115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e7008c2-abaf-45ae-8b13-5e44351b3257 · outbound

This paper cites The RVQ model disentangles speaker-specific la- tents and reconstructs watermarked audio.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents The RVQ model disentangles speaker-specific la- tents and reconstructs watermarked audio

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:49.916550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7c24cade-15fa-4c13-87c6-cd4e09f82949 · outbound

This paper cites Implementation Details For the RVQ model, we use the pretrained SpeechTokenizer *.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Implementation Details For the RVQ model, we use the pretrained SpeechTokenizer *

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:49.783309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ab851a6b-e778-4f76-8afd-7f0d2b9de3ca · outbound

This paper cites Additionally, we incorporate VC-simulated augmenta- tions and V AD-based loss to further enhance the robustness of V oiceMark.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Additionally, we incorporate VC-simulated augmenta- tions and V AD-based loss to further enhance the robustness of V oiceMark

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:49.448395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a051ce5e-b760-4763-bb4b-cbbb5527256d · outbound

This paper cites an unresolved cited work.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:52:49.231357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 560a1257-afe8-4ed8-8c14-f2c1930dff7f · outbound

This paper cites Gruhl, A.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Gruhl, A

Reference 6

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:52:48.861485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a5a68e83-f819-4cbc-be9d-869bdade2d28 · outbound

This paper cites De- tecting voice cloning attacks via timbre watermarking,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents De- tecting voice cloning attacks via timbre watermarking,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:49.052030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 14a77150-a91c-43f9-b55a-f36d57b18d1f · outbound

This paper cites CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:44.234690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a21cbe0-c959-4c9d-a419-20ec1b584fe1 · outbound

This paper cites F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:44.357485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf0e8148-8995-4008-a43f-61aa484e8827 · outbound

This paper cites Maskgct: Zero-shot text- to-speech with masked generative codec transformer,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Maskgct: Zero-shot text- to-speech with masked generative codec transformer,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:44.467258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 649eecf1-d788-43d8-bec7-b248dfbb6a4d · outbound

This paper cites Techniques for data hiding,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Techniques for data hiding,

Reference 11

Resolution: verified exact; doi, observed 2026-08-07T13:52:46.793038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 62a4c0e3-aa0a-4d7c-b30e-95062793a035 · outbound

This paper cites Natural tts synthesis by conditioning wavenet on mel spectrogram pre- dictions,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Natural tts synthesis by conditioning wavenet on mel spectrogram pre- dictions,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:45.160070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d766219-fc65-47e1-af2d-db940381b093 · outbound

This paper cites WavMark: Watermarking for Audio Generation.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents WavMark: Watermarking for Audio Generation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:44.744029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 679ef444-a4ce-4a87-87c4-17c4928f9f78 · outbound

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

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Proactive detection of voice cloning with localized watermarking,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:48.630720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 46b1198a-d9e1-4d0b-a99b-3ce91b446d1d · outbound

This paper cites Proactive audio authentication using speaker identity watermarking,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Proactive audio authentication using speaker identity watermarking,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:48.445724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0078746f-1c65-45b0-893f-30698b2d6876 · outbound

This paper cites The model is trained for 30 epochs using Adam [21] optimizer with a learning rate of5e −5.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents The model is trained for 30 epochs using Adam [21] optimizer with a learning rate of5e −5

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:49.598054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b931714d-b772-45de-8ccb-e266c0c7ce43 · outbound

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

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:48.273468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 976f6a41-62af-483b-981c-12e41c5378b2 · outbound

This paper cites Fastspeech 2: Fast and high-quality end-to-end text to speech,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Fastspeech 2: Fast and high-quality end-to-end text to speech,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:48.050691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3af694f5-0558-46a4-9409-bb198c8254e4 · outbound

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

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Paddlespeech: An easy-to-use all-in-one speech toolkit,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:47.880357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9c6a3a09-5827-421e-93d8-7158dcba402c · outbound

This paper cites V oice cloning app,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents V oice cloning app,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:47.694277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a749c905-0668-4cb1-baab-5bb29dd0c58a · outbound

This paper cites High Fidelity Neural Audio Compression.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents High Fidelity Neural Audio Compression

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:45.548593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002776d9-c8c4-49d0-91e6-90e661347c88 · outbound

This paper cites Naturalspeech 3: Zero-shot speech syn- thesis with factorized codec and diffusion models,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Naturalspeech 3: Zero-shot speech syn- thesis with factorized codec and diffusion models,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:47.510021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9b249c78-daf0-46a8-8de0-3b860e34aaf8 · outbound

This paper cites SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:45.708799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbd3d8e2-cbf4-4d6a-a3ec-91ec5318cc8d · outbound

This paper cites Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:45.803244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 700e9ca6-7118-4184-809e-16431506b768 · outbound

This paper cites Attention is all you need,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Attention is all you need,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:45.924595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67507c36-7537-48e0-8f02-75cd0581a9cf · outbound

This paper cites an unresolved cited work.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:52:47.346618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation da792311-bb83-416b-a441-ed529c7d588f · outbound

This paper cites Adam: A Method for Stochastic Optimization.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Adam: A Method for Stochastic Optimization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:46.120612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 596e068b-2eae-4c61-8935-c327a1f48739 · outbound

This paper cites English multi-speaker corpus for cstr voice cloning toolkit,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents English multi-speaker corpus for cstr voice cloning toolkit,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:47.154984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 721db919-dc4f-4f5c-b955-c534076d8de0 · outbound

This paper cites Lib- rispeech: an asr corpus based on public domain audio books,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Lib- rispeech: an asr corpus based on public domain audio books,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:46.316770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f46d6f39-d03b-47cc-8008-0261a0161b4b · outbound

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

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:46.436359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9258956e-4e59-4fcd-99ad-f12a4b3213c1 · outbound

This paper cites A short- time objective intelligibility measure for time-frequency weighted noisy speech,.

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents A short- time objective intelligibility measure for time-frequency weighted noisy speech,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:52:47.016246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation ea8d6b6c-5020-4ef9-b1f5-c9b285b97071 · inbound