Paper Citation Record · LEDGER

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models

As of 13 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 1 inbound Pith citation observation for arXiv:2506.03364.

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

pith.paper-citation-record.v1
2506.03364 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:09:27.471742Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:09:24.996793Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T11:09:27.678728Z

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy14
unresolved12
parse uncertain0
malformed identifier3
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bf5d19be-3b09-4468-8649-365e3b56b752 · outbound

This paper cites Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T11:09:27.826462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d3a3e3e5-0f49-4091-849a-5f3dfe8cce50 · outbound

This paper cites Speech Foundation Models : We consider WavLM1 [14] and Unispeech-SAT2 [15] which are SOTA SFMs in SUPERB.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Speech Foundation Models : We consider WavLM1 [14] and Unispeech-SAT2 [15] which are SOTA SFMs in SUPERB

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:30.324853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 679dcff9-5944-4529-bb9a-285cd88e275a · outbound

This paper cites We implemented two distinct downstream for individual FMs—Fully Connected Network (FCN) and CNN.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models We implemented two distinct downstream for individual FMs—Fully Connected Network (FCN) and CNN

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:30.233288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation dbe3c320-203c-41a4-83af-67f9d25ce94d · outbound

This paper cites Dataset We utilized the CtrSVDD [24], a benchmark dataset specifically designed for SVDD and the audio samples are in Chinese and Japanese.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Dataset We utilized the CtrSVDD [24], a benchmark dataset specifically designed for SVDD and the audio samples are in Chinese and Japanese

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:09:30.146119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8d79b767-cba9-4e32-9522-8ace14960afe · outbound

This paper cites Table 2 presents the evaluation scores for modeling with various combinations of SFMs.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Table 2 presents the evaluation scores for modeling with various combinations of SFMs

Reference 5

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:09:30.072457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f0c74d4a-3202-48ab-88a9-c0cc5e74d64b · outbound

This paper cites MMFMs such as IB and LB, excel in capturing source-specific traits like timbre, pitch manipulation, and synthesis artifacts due to their cross- modal pretraining.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models MMFMs such as IB and LB, excel in capturing source-specific traits like timbre, pitch manipulation, and synthesis artifacts due to their cross- modal pretraining

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:30.002183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 68bce3c9-6dce-43cf-9ec2-b63feadaeb2c · outbound

This paper cites Singfake: Singing voice deepfake detection,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Singfake: Singing voice deepfake detection,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:29.927959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b5eb863e-249c-4657-868d-3723ece30843 · outbound

This paper cites Ctrsvdd: A benchmark dataset and baseline analysis for controlled singing voice deepfake detection,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Ctrsvdd: A benchmark dataset and baseline analysis for controlled singing voice deepfake detection,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:29.860741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1048414a-db4e-4081-a730-fa67b6abafa5 · outbound

This paper cites Svdd 2024: The inaugural singing voice deepfake detection chal- lenge,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Svdd 2024: The inaugural singing voice deepfake detection chal- lenge,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:29.805212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4f667a30-42b5-4b98-abd0-2f903da00376 · outbound

This paper cites Source tracing: Detect- ing voice spoofing,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Source tracing: Detect- ing voice spoofing,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:29.757860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 591a3f07-e0c7-413e-aaa0-759cb463d0ea · outbound

This paper cites An initial investigation for detecting vocoder fingerprints of fake audio,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models An initial investigation for detecting vocoder fingerprints of fake audio,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:29.629903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5b6b559f-fe18-4f87-90ef-964bf6359719 · outbound

This paper cites Distinguish- ing neural speech synthesis models through fingerprints in speech waveforms,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Distinguish- ing neural speech synthesis models through fingerprints in speech waveforms,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:29.399707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d0a2692a-b86d-4811-8d03-098f21af0a81 · outbound

This paper cites Attacker attribution of audio deepfakes,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Attacker attribution of audio deepfakes,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:29.126713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 52489c2d-efab-442d-93eb-61e994244288 · outbound

This paper cites Source tracing of audio deepfake systems,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Source tracing of audio deepfake systems,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:28.900095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 478a36bd-6600-4e79-8918-c11b2d2d8ee7 · outbound

This paper cites Attribu- tion of diffusion based deepfake speech generators,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Attribu- tion of diffusion based deepfake speech generators,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:28.659768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d6129c11-13f2-48a8-a410-d86cc4314456 · outbound

This paper cites Heterogeneity over homogeneity: Investigating multilingual speech pre-trained models for detecting audio deepfake,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Heterogeneity over homogeneity: Investigating multilingual speech pre-trained models for detecting audio deepfake,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.013846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb039946-97e3-4a0b-a850-d9025936e263 · outbound

This paper cites Singing voice graph modeling for singfake detection,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Singing voice graph modeling for singfake detection,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:28.417239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d8723da1-61c5-4899-adbf-30b6a2428b1f · outbound

This paper cites Investi- gation of ensemble features of self-supervised pretrained models for automatic speech recognition,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Investi- gation of ensemble features of self-supervised pretrained models for automatic speech recognition,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.157753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb87ff66-0a6a-4a5c-95f1-95a181ee0a21 · outbound

This paper cites Speech foundation model ensembles for the controlled singing voice deep- fake detection (ctrsvdd) challenge 2024,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Speech foundation model ensembles for the controlled singing voice deep- fake detection (ctrsvdd) challenge 2024,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:28.180367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9dc6690b-1a82-42a6-8356-8b71f414ec60 · outbound

This paper cites wav2vec 2.0: A framework for self-supervised learning of speech representations,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models wav2vec 2.0: A framework for self-supervised learning of speech representations,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.303298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac6c5fb-6d22-4294-9b4c-19724ceed1d5 · outbound

This paper cites Unispeech-sat: Universal speech repre- sentation learning with speaker aware pre-training,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Unispeech-sat: Universal speech repre- sentation learning with speaker aware pre-training,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.366094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb05424c-e5a7-46f8-b6be-cbeef6e447cb · outbound

This paper cites Xls-r: Self-supervised cross-lingual speech representation learning at scale,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Xls-r: Self-supervised cross-lingual speech representation learning at scale,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.435761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fba6c34-fec5-41e4-a3c7-4dfdc2b7c4e4 · outbound

This paper cites Robust speech recognition via large-scale weak supervision,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Robust speech recognition via large-scale weak supervision,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.502914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46591a55-2116-4698-8ede-2034bc7c413a · outbound

This paper cites Scaling speech technology to 1,000+ languages,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Scaling speech technology to 1,000+ languages,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.571595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 117de633-59f5-4f2e-a612-26b40c75f1d7 · outbound

This paper cites X-vectors: Robust dnn embeddings for speaker recognition,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models X-vectors: Robust dnn embeddings for speaker recognition,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.716713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4069a85-3333-437f-b636-a2c8f78ba737 · outbound

This paper cites MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.894022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d83bd0d5-9e9d-4d74-bb6a-96484dde7067 · outbound

This paper cites MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.953234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97af3196-4099-4190-88ef-d456c4532621 · outbound

This paper cites Imagebind: One embedding space to bind them all,.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Imagebind: One embedding space to bind them all,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:27.157036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 425a999f-4e97-46bf-aaea-b4196c0982ac · outbound

This paper cites LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:27.322111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92b3bf40-c88b-4494-8d00-2fa2570df64e · outbound

This paper cites Svdd challenge 2024: A singing voice deepfake detection challenge (ctrsvdd track, training/development set),.

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Svdd challenge 2024: A singing voice deepfake detection challenge (ctrsvdd track, training/development set),

Reference 30

Resolution: malformed identifier; no resolver link, observed 2026-08-07T11:09:27.471742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bf5d19be-3b09-4468-8649-365e3b56b752 · inbound