Paper Citation Record · LEDGER

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models

As of 12 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2607.16870.

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

pith.paper-citation-record.v1
2607.16870 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T19:47:30.104529Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

40 of 40 outbound references displayed

verified exact0
verified fuzzy0
unresolved40
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b41ccd79-4a83-44e5-a495-b1b86223666b · outbound

This paper cites The secret revealer: Generative model-inversion attacks against deep neural networks,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models The secret revealer: Generative model-inversion attacks against deep neural networks,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:24.390762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25f13f89-60bd-4684-adfc-2734eeee36e3 · outbound

This paper cites SpeechGPT: Empowering large language models with intrinsic cross- modal conversational abilities,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models SpeechGPT: Empowering large language models with intrinsic cross- modal conversational abilities,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:24.491640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5579030-ac7e-4164-b092-e5d31aab4ef5 · outbound

This paper cites Spoken question answering and speech continuation using spectrogram-powered LLM,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Spoken question answering and speech continuation using spectrogram-powered LLM,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:24.553795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08e535a6-26b3-43b6-b805-683ca1c7f895 · outbound

This paper cites PSLM: Parallel generation of text and speech with LLMs for low-latency spoken dialogue systems,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models PSLM: Parallel generation of text and speech with LLMs for low-latency spoken dialogue systems,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:24.628423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b398e019-1841-4b03-8f55-3d819d4977fc · outbound

This paper cites Moshi: a speech-text foundation model for real-time dialogue.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Moshi: a speech-text foundation model for real-time dialogue

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:24.701159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13531619-6790-4625-8624-fb6d76310337 · outbound

This paper cites Higgs TTS 3: Conversational speech for voice AI from Boson AI,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Higgs TTS 3: Conversational speech for voice AI from Boson AI,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:24.778375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfd9be4d-22fd-44fa-a6e3-d4ba67094e22 · outbound

This paper cites OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:24.839553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 657f12c3-9cdb-437d-a131-940e6b9c519e · outbound

This paper cites Kimi-Audio Technical Report.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Kimi-Audio Technical Report

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:24.929258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02662e63-3c0c-4ba8-9f46-e0378173033c · outbound

This paper cites Qwen3-Omni Technical Report.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Qwen3-Omni Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:25.092934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f59a965-2629-4dcb-b7be-ad8185eeaeba · outbound

This paper cites Speaker verification using adapted gaussian mixture models,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Speaker verification using adapted gaussian mixture models,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:25.330783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ce85e1-15b4-4f02-a9ea-c789dcf2d52e · outbound

This paper cites Joint factor analysis versus eigenchannels in speaker recognition,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Joint factor analysis versus eigenchannels in speaker recognition,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:25.526470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b07f127a-4e88-4d7f-b6d2-243feea5dac9 · outbound

This paper cites Front- end factor analysis for speaker verification,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Front- end factor analysis for speaker verification,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:25.700973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 023a8b05-ae8d-404a-8c4e-a59b7f86925a · outbound

This paper cites Deep neural networks for small footprint text-dependent speaker verification,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Deep neural networks for small footprint text-dependent speaker verification,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:25.875069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf4ef308-20af-4ee3-9a74-021fe5783dc3 · outbound

This paper cites End-to-end text-dependent speaker verification,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models End-to-end text-dependent speaker verification,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:25.988124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06986d7c-604b-4589-82bb-53ab907588eb · outbound

This paper cites Generalized end- to-end loss for speaker verification,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Generalized end- to-end loss for speaker verification,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:26.167636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae4c98e0-78f5-4f48-9ec5-100ff276566f · outbound

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

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models X-vectors: Robust DNN embeddings for speaker recognition,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:26.321678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92b0f91e-e2f8-4a9d-a1dd-73a6ebe60a56 · outbound

This paper cites V oxCeleb2: Deep speaker recognition,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models V oxCeleb2: Deep speaker recognition,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:26.493248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 782a5783-d868-49e9-b65c-26ac06f3da0a · outbound

This paper cites Pushing the limits of self-supervised speaker verification using regularized distillation framework,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Pushing the limits of self-supervised speaker verification using regularized distillation framework,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:26.667982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43107838-82ed-4985-9da5-9d12c2885b81 · outbound

This paper cites Self-distillation prototypes network: Learning robust speaker representations without supervision,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Self-distillation prototypes network: Learning robust speaker representations without supervision,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:26.806015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 619ed206-5b0e-484a-8faa-ac6356778bde · outbound

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

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:26.890577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 335f5300-8540-412b-b2b6-ce7c22a8aee0 · outbound

This paper cites CAM++: A fast and efficient network for speaker verification using context- aware masking,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models CAM++: A fast and efficient network for speaker verification using context- aware masking,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:26.994800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf96013c-2dd7-4657-8a4f-a48b5505175c · outbound

This paper cites An enhanced Res2Net with local and global feature fusion for speaker verifi- cation,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models An enhanced Res2Net with local and global feature fusion for speaker verifi- cation,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:27.129739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faf2f83c-520f-4d71-90d8-50a20ebe0675 · outbound

This paper cites Model inversion attacks that exploit confidence information and basic countermeasures,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Model inversion attacks that exploit confidence information and basic countermeasures,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:27.335806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77690235-ea4c-4a09-84ec-b9f109fc4728 · outbound

This paper cites FGMIA: Feature- guided model inversion attacks against face recognition models,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models FGMIA: Feature- guided model inversion attacks against face recognition models,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:27.424163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15486223-7b4f-4186-a719-0841cd93425b · outbound

This paper cites Model Inversion Attacks Through Target-Specific Conditional Diffusion Models.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Model Inversion Attacks Through Target-Specific Conditional Diffusion Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:27.549176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1063ac30-3287-466d-83ea-15c8e10df02e · outbound

This paper cites Text embeddings reveal (almost) as much as text,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Text embeddings reveal (almost) as much as text,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:27.730257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00345a64-b265-44a7-b9cf-a00b1ce6ef74 · outbound

This paper cites Text embedding inversion security for multilingual language models,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Text embedding inversion security for multilingual language models,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:27.951493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a18cd1e9-9536-467e-90cc-e2e323f25591 · outbound

This paper cites Introducing model inversion attacks on automatic speaker recognition,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Introducing model inversion attacks on automatic speaker recognition,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:28.093709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58b1bb36-ee6b-4c0c-a2cf-3a0bf3c05f9b · outbound

This paper cites Inference attacks for x-vector speaker anonymization,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Inference attacks for x-vector speaker anonymization,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:28.297263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6124d17a-d751-4de8-a900-b963ee74aec7 · outbound

This paper cites V oxGuard: Evaluating user and attribute privacy in speech via membership inference attacks,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models V oxGuard: Evaluating user and attribute privacy in speech via membership inference attacks,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:28.438714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ba8d875-a5e9-4212-9f11-2d9d0e0e3262 · outbound

This paper cites Scores know Bob’s voice: Speaker impersonation attack,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Scores know Bob’s voice: Speaker impersonation attack,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:28.657035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f20e806-1730-4687-9f73-a0bc9a1dce0d · outbound

This paper cites HearSay benchmark: Do audio LLMs leak what they hear?.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models HearSay benchmark: Do audio LLMs leak what they hear?

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:28.831537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 143bdb3a-fe9a-4b5f-8f00-5f3c85157300 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models An image is worth 16x16 words: Transformers for image recognition at scale,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:29.024367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da2a316b-2924-4b18-a935-4f5e41fae4c0 · outbound

This paper cites BERT: Pre-training of deep bidirectional transformers for language understanding,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models BERT: Pre-training of deep bidirectional transformers for language understanding,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:29.199656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78f18058-1c52-4792-ba3b-5f115970af09 · outbound

This paper cites Layer Normalization.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Layer Normalization

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:29.394242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acaed446-cec7-49f2-a2be-c0a305b8616f · outbound

This paper cites Gaussian Error Linear Units (GELUs).

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Gaussian Error Linear Units (GELUs)

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:29.574585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb9b4594-bc14-4507-8af0-3f75795c0905 · outbound

This paper cites VICReg: Variance-invariance- covariance regularization for self-supervised learning,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models VICReg: Variance-invariance- covariance regularization for self-supervised learning,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:29.739265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9584add1-68cf-4f55-a963-a925199d8bef · outbound

This paper cites Emerging properties in self-supervised vision transformers,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models Emerging properties in self-supervised vision transformers,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:29.881362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07481413-0a10-42a4-9d15-77950c76f611 · outbound

This paper cites ArcFace: Additive angular margin loss for deep face recognition,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models ArcFace: Additive angular margin loss for deep face recognition,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:29.994945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 655d3997-f351-43e8-8ec4-7c45a91eebd2 · outbound

This paper cites V oxCeleb: A large- scale speaker identification dataset,.

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models V oxCeleb: A large- scale speaker identification dataset,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T19:47:30.104529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.