Paper Citation Record · LEDGER

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark

As of 7 August 2026, this Paper Citation Record lists 73 of 73 outbound references and 4 inbound Pith citation observations for arXiv:2508.04143.

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

pith.paper-citation-record.v1
2508.04143 v1

Coverage vector

measured 73 of 73 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T00:56:07.006881Z

measured 77 of 77 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T00:55:59.944344Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T07:47:44.705491Z

Reference resolution

73 of 73 outbound references displayed

verified exact3
verified fuzzy60
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation eee9ee7d-06e4-4f97-86d4-49a2868462e7 · outbound

This paper cites Multilingual Source Tracing of Speech Deepfakes: A First Benchmark.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Multilingual Source Tracing of Speech Deepfakes: A First Benchmark

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T00:55:59.944344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56349248-f892-4998-b83d-e720165950c0 · outbound

This paper cites an unresolved cited work.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-06T00:56:18.247231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 83656398-b823-47f4-a5a5-5585f6495218 · outbound

This paper cites ST Models This section introduces the models used for ST tasks.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark ST Models This section introduces the models used for ST tasks

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:18.066684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ce65c883-ef87-4226-9074-6058fd955c4f · outbound

This paper cites an unresolved cited work.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Unresolved cited work

Reference 4

Resolution: verified exact; raw_fallback, observed 2026-08-06T00:56:07.874543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bb93b1e8-59f6-47d8-92ee-78fb46080183 · outbound

This paper cites Furthermore, we first explore the effects of unseen languages and speakers in ST tasks.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Furthermore, we first explore the effects of unseen languages and speakers in ST tasks

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:17.887350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ae01e7da-84fb-40b2-b708-0e1beaa4450a · outbound

This paper cites V oxpopulitts: a large-scale multilingual tts corpus for zero-shot speech generation,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark V oxpopulitts: a large-scale multilingual tts corpus for zero-shot speech generation,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:17.677167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 967ec552-e756-4390-ae01-ca5544bdb30f · outbound

This paper cites Promptvc: Flexible stylistic voice conversion in latent space driven by natural language prompts,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Promptvc: Flexible stylistic voice conversion in latent space driven by natural language prompts,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:17.483399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6e42808d-eb7f-4833-b596-c98a4085bc82 · outbound

This paper cites A survey on speech deep- fake detection,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark A survey on speech deep- fake detection,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:17.272994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aa6542d7-7241-460d-8fbd-8c936adb741e · outbound

This paper cites Scams and frauds in the digital age: Ml-based detection and prevention strategies,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Scams and frauds in the digital age: Ml-based detection and prevention strategies,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:17.116700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a4720805-098c-4e50-b9e4-6359792202e5 · outbound

This paper cites Ge-gnn: Gated edge-augmented graph neural network for fraud detection,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Ge-gnn: Gated edge-augmented graph neural network for fraud detection,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:16.925443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1178f371-21f6-44bc-b078-ab8fa6c1de14 · outbound

This paper cites Crowd density estimation based on multi-level attention maps,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Crowd density estimation based on multi-level attention maps,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:16.777335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e8bd0b89-731c-4ef9-8408-f0e95b43a8d9 · outbound

This paper cites Frect: Frequency-augmented convolu- tional transformer for robust time series anomaly detection,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Frect: Frequency-augmented convolu- tional transformer for robust time series anomaly detection,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:16.666041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fede622c-f34f-48a6-a5ed-f99a9cc74ec4 · outbound

This paper cites Decomposition-based multi-scale transformer framework for time series anomaly detection,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Decomposition-based multi-scale transformer framework for time series anomaly detection,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:16.485598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 08918162-dce4-4e0c-8dd4-0371f4e6b984 · outbound

This paper cites Asvspoof 2021: To- wards spoofed and deepfake speech detection in the wild,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Asvspoof 2021: To- wards spoofed and deepfake speech detection in the wild,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:16.311024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 55572476-b84f-475c-9a61-c84e07adfdb7 · outbound

This paper cites Asvspoof 5: Crowdsourced speech data, deepfakes, and adversarial attacks at scale,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Asvspoof 5: Crowdsourced speech data, deepfakes, and adversarial attacks at scale,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:16.130982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5a73b0e2-d8cb-416b-9937-5f1a2ddb12e1 · outbound

This paper cites Add 2022: The first audio deep synthesis detection challenge,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Add 2022: The first audio deep synthesis detection challenge,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:16.015889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 28d06135-1de1-4c0e-b633-afb3ccdcb011 · outbound

This paper cites Add 2023: The second audio deep- fake detection challenge,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Add 2023: The second audio deep- fake detection challenge,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:15.860576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4101efc8-ef66-43c0-b377-b6cb9d2479c6 · outbound

This paper cites Trident of poseidon: A generalized approach for detecting deepfake voices,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Trident of poseidon: A generalized approach for detecting deepfake voices,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:15.690594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 64e5bd5a-5e7f-4d1e-b752-dcf9c086976b · outbound

This paper cites Xlsr-mamba: A dual-column bidirec- tional state space model for spoofing attack detection,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Xlsr-mamba: A dual-column bidirec- tional state space model for spoofing attack detection,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:15.538809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 58d09424-e207-40c8-8724-545deb5c3d33 · outbound

This paper cites Nes2net: A lightweight nested architecture for foundation model driven speech anti-spoofing,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Nes2net: A lightweight nested architecture for foundation model driven speech anti-spoofing,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T00:56:01.842439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5254a8b5-7b4b-4fc9-a5b2-68d83211e416 · outbound

This paper cites Interpretable temporal class activation representation for audio spoofing detection,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Interpretable temporal class activation representation for audio spoofing detection,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:15.373056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1d3052c4-b041-4eef-a583-75c62baf6f0e · outbound

This paper cites Speech watermarking: An approach for the forensic analysis of digital telephonic recordings,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Speech watermarking: An approach for the forensic analysis of digital telephonic recordings,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:15.229590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 37358d63-a196-433a-9053-1a1f5a7dfb76 · outbound

This paper cites Digital image foren- sics via intrinsic fingerprints,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Digital image foren- sics via intrinsic fingerprints,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:15.059054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d2c65c68-0f4e-4f88-9bc4-9d863ff7972c · outbound

This paper cites Forensic analysis and anonymization of printed documents,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Forensic analysis and anonymization of printed documents,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:14.953165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ad8e7d0d-dc5a-474c-833e-d9175e36b487 · outbound

This paper cites Transformer for authenticating the source microphone in digital audio forensics,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Transformer for authenticating the source microphone in digital audio forensics,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:14.848103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 60e8f7cb-4a42-46e7-a5e3-b6ab2276717e · outbound

This paper cites Primek-net: Multi- scale spectral learning via group prime-kernel convolutional neu- ral networks for single channel speech enhancement,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Primek-net: Multi- scale spectral learning via group prime-kernel convolutional neu- ral networks for single channel speech enhancement,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:14.743805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3382003a-ff3d-4549-a42a-befa12a45748 · outbound

This paper cites Guidelines on cell phone forensics,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Guidelines on cell phone forensics,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:14.634731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cf32e523-1269-4edd-9360-9b2346fd045c · outbound

This paper cites Source cell-phone recognition from recorded speech using non-speech segments,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Source cell-phone recognition from recorded speech using non-speech segments,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:14.467337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f404b511-58e9-443c-af46-6a313b632f34 · outbound

This paper cites Forensic analysis of phone call networks,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Forensic analysis of phone call networks,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:14.264129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eafc6215-46f5-4fe5-b0b4-6c63e0b63291 · outbound

This paper cites Addressing Noise and Stochasticity in Fraud Detection for Service Networks.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Addressing Noise and Stochasticity in Fraud Detection for Service Networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T00:56:02.920597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19a7abc9-5459-4a15-9fed-543e378e45b6 · outbound

This paper cites Source tracing of audio deepfake systems,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Source tracing of audio deepfake systems,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:14.134743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1e9a8fc7-46b2-415f-b327-a3fbb29e9626 · outbound

This paper cites Generalized source tracing: Detect- ing novel audio deepfake algorithm with real emphasis and fake dispersion strategy,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Generalized source tracing: Detect- ing novel audio deepfake algorithm with real emphasis and fake dispersion strategy,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:13.996714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a7513c1d-727f-4e63-a225-aab2471085a3 · outbound

This paper cites Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T00:56:03.182937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eac11690-e0f1-44d3-9d81-2f1b7c30b772 · outbound

This paper cites Multilingual speech translation from efficient finetuning of pretrained models,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Multilingual speech translation from efficient finetuning of pretrained models,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:13.828973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9fd16104-5ca3-4827-a987-796525d6563c · outbound

This paper cites Solving the unsolvable: Translating case law in hong kong,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Solving the unsolvable: Translating case law in hong kong,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:13.674857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 00e4b416-629c-489c-96ee-92fc0653910f · outbound

This paper cites Multi-scene ro- bust speaker verification system built on improved ecapa-tdnn,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Multi-scene ro- bust speaker verification system built on improved ecapa-tdnn,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:12.498785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9786e7e2-96f6-4a15-8928-b21ab0fadf8c · outbound

This paper cites TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Law.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark TransLaw: A Large-Scale Dataset and Multi-Agent Benchmark Simulating Professional Translation of Hong Kong Case Law

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T00:56:03.545227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b957727f-eccb-4d3c-944a-f7ea871ec660 · outbound

This paper cites Probing the feasibility of mul- tilingual speaker anonymization,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Probing the feasibility of mul- tilingual speaker anonymization,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:13.513840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2f85fa83-f9a0-4a3e-a484-23b5c9735d62 · outbound

This paper cites Introducing multilingual pho- netic information to speaker embedding for speaker verification,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Introducing multilingual pho- netic information to speaker embedding for speaker verification,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:13.228239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3d4f59a2-7652-4d25-8c7b-c2b3532fa9db · outbound

This paper cites Research on front-end of asv system based on mel spectrum in noise scenario,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Research on front-end of asv system based on mel spectrum in noise scenario,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:12.891550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bacc259c-4c30-4196-bce3-05fd809ac478 · outbound

This paper cites Research on acoustic feature extractor for automatic speaker verification systerm,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Research on acoustic feature extractor for automatic speaker verification systerm,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:12.687581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1afa8729-0b48-4082-8c8a-738a29503a33 · outbound

This paper cites Madd: A multi-lingual multi-speaker audio deepfake detection dataset,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Madd: A multi-lingual multi-speaker audio deepfake detection dataset,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:11.589663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a10be848-2578-4218-9daa-c8c290370de6 · outbound

This paper cites Research on speaker identifica- tion models based on cnn and additive angular margin loss,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Research on speaker identifica- tion models based on cnn and additive angular margin loss,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:12.324043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4f30c6b4-bac2-4f2b-b825-71070d464d6b · outbound

This paper cites Conformer-based speaker recogni- tion model for real-time multi-scenarios,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Conformer-based speaker recogni- tion model for real-time multi-scenarios,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:12.192642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c9d4cee2-0a91-4799-8c36-bb94fd8ac5db · outbound

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

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Scaling speech technology to 1,000+ languages,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:12.036975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5fc77ba6-dca7-4e28-a1eb-df92620a04e3 · outbound

This paper cites Neural codec language models are zero-shot text to speech synthesizers,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Neural codec language models are zero-shot text to speech synthesizers,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:11.880182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e9ff347f-d20a-4f31-a051-0f75cc31cff0 · outbound

This paper cites Polyglotfake: A novel multilingual and multimodal deepfake dataset,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Polyglotfake: A novel multilingual and multimodal deepfake dataset,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:11.736451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fd3dd8cc-d7c3-4a43-9224-d7184b963d71 · outbound

This paper cites MUSAN: A Music, Speech, and Noise Corpus.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark MUSAN: A Music, Speech, and Noise Corpus

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T00:56:05.111511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ee83dc-8e2b-40d1-a4d6-48b14d2fdcb8 · outbound

This paper cites Mlaad: The multi- language audio anti-spoofing dataset,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Mlaad: The multi- language audio anti-spoofing dataset,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:11.478947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3d368de1-c577-4638-9f2e-6ae12db016d9 · outbound

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

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Heterogeneity over homogeneity: Investigating multilingual speech pre-trained models for detecting audio deepfake,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:11.344934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b8d4906-80f4-4037-adf5-6ad719b7226b · outbound

This paper cites Transferring audio deepfake detection capability across lan- guages,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Transferring audio deepfake detection capability across lan- guages,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:11.143453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 09d36118-c90a-4228-a268-b0a937053c4e · outbound

This paper cites Towards quantifying and reducing language mismatch ef- fects in cross-lingual speech anti-spoofing,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Towards quantifying and reducing language mismatch ef- fects in cross-lingual speech anti-spoofing,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:11.001860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 90ae49ac-2900-4611-8d86-d85c891c226b · outbound

This paper cites Are audio DeepFake detection models polyglots?.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Are audio DeepFake detection models polyglots?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T00:56:05.043440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 516e640b-a9a9-41e6-8f5e-9c7a0e120324 · outbound

This paper cites Aasist: Audio anti-spoofing us- ing integrated spectro-temporal graph attention networks,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Aasist: Audio anti-spoofing us- ing integrated spectro-temporal graph attention networks,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:10.111373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 76d3647a-110d-4bea-ba6e-371533564d59 · outbound

This paper cites Shortcut learning in deep neural networks,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Shortcut learning in deep neural networks,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:10.817527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9873d17d-896c-46d2-b3eb-40784435531d · outbound

This paper cites Ecapa2: A hybrid neural net- work architecture and training strategy for robust speaker embed- dings,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Ecapa2: A hybrid neural net- work architecture and training strategy for robust speaker embed- dings,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:10.669302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a579830c-3627-4dc2-8d1d-28b2c76003c6 · outbound

This paper cites Concept decompositions for large sparse text data using clustering,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Concept decompositions for large sparse text data using clustering,

Reference 57

Resolution: verified exact; doi, observed 2026-08-06T00:56:07.194218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dbf9e1c0-c1eb-4bc4-9ddc-265a812e853d · outbound

This paper cites Review on determining number of cluster in k-means clustering,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Review on determining number of cluster in k-means clustering,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:10.465100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e91df8d7-0cd8-477b-9fe0-cf8a1eddcc8a · outbound

This paper cites A comparison of features for synthetic speech detection,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark A comparison of features for synthetic speech detection,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:10.266093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c61d3539-4c7a-4245-a015-6232547136b2 · outbound

This paper cites Common V oice: A massively-multilingual speech corpus,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Common V oice: A massively-multilingual speech corpus,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:09.218746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 40b9ace0-5bb2-4ccc-a10f-8661647d8d2f · outbound

This paper cites Deep residual learning for image recognition,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Deep residual learning for image recognition,

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T00:56:05.806000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2423df7-60c4-4143-a36f-a1376ea346ed · outbound

This paper cites ECAPA- TDNN: Emphasized channel attention, propagation and aggrega- tion in TDNN based speaker verification,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark ECAPA- TDNN: Emphasized channel attention, propagation and aggrega- tion in TDNN based speaker verification,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:09.939039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation edb00b6a-3a84-4463-a96c-58ae836c9342 · outbound

This paper cites Unsu- pervised cross-lingual representation learning for speech recogni- tion,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Unsu- pervised cross-lingual representation learning for speech recogni- tion,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:09.759102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8651a924-bad0-4147-ae96-f32a9f898d27 · outbound

This paper cites V oxpopuli: A large-scale multilingual speech corpus for representation learning, semi- supervised learning and interpretation,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark V oxpopuli: A large-scale multilingual speech corpus for representation learning, semi- supervised learning and interpretation,

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:09.570969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d345779e-6c42-4f7a-99f8-9353489a22fc · outbound

This paper cites MLS: A large-scale multilin- gual dataset for speech research,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark MLS: A large-scale multilin- gual dataset for speech research,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:09.385741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e236270a-e5d2-4ea3-a3fe-6584f760c568 · outbound

This paper cites mixup: Beyond Empirical Risk Minimization.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark mixup: Beyond Empirical Risk Minimization

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T00:56:06.907770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 849cdd31-960d-46ec-ae65-33a18129af6c · outbound

This paper cites V oxlingua107: A dataset for spoken lan- guage recognition,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark V oxlingua107: A dataset for spoken lan- guage recognition,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:08.986663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 653873a3-b03b-4db6-a48d-5b608aae17f3 · outbound

This paper cites Speech recog- nition and keyword spotting for low-resource languages: Babel project research at cued,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Speech recog- nition and keyword spotting for low-resource languages: Babel project research at cued,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:08.731722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ebc521c7-cc74-475a-bca3-f230ded0ba12 · outbound

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

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark wav2vec 2.0: A framework for self-supervised learning of speech represen- tations,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:08.544693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2fbbd414-1fdf-4d6a-9016-347bed2e2c9e · outbound

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

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Lib- rispeech: An asr corpus based on public domain audio books,

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:08.355635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 52fd4e74-5343-4c5d-9f01-c63832aa2062 · outbound

This paper cites Towards generalisable and calibrated audio deepfake detection with self-supervised represen- tations,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Towards generalisable and calibrated audio deepfake detection with self-supervised represen- tations,

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:08.176258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3b6a9171-82e2-4b3f-9907-dac1fada41bf · outbound

This paper cites Unlocking the full potential of separa- ble convolutions on tensor cores,.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Unlocking the full potential of separa- ble convolutions on tensor cores,

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T00:56:08.027260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5966257d-e303-4ecc-a9bd-047f8192b98a · outbound

This paper cites Available: https://arxiv.org/abs/2501.09444.

Multilingual Source Tracing of Speech Deepfakes: A First Benchmark Available: https://arxiv.org/abs/2501.09444

Reference 2025

Resolution: verified exact; raw_fallback, observed 2026-08-06T00:56:07.497074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation eee9ee7d-06e4-4f97-86d4-49a2868462e7 · inbound