Paper Citation Record · LEDGER

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations

As of 10 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 3 inbound Pith citation observations for arXiv:2507.02927.

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

pith.paper-citation-record.v1
2507.02927 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:42:24.102738Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:42:22.092467Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-10T12:15:01.137692Z

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy13
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 131ec8f9-b6ac-4ff5-85bf-65484850585e · outbound

This paper cites an unresolved cited work.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:26.973167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 972f97d3-9aa0-413e-9205-bbe5055e1865 · outbound

This paper cites A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:22.092467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 613fb2ed-1c0f-4087-bbd9-e5fb87e779b8 · outbound

This paper cites an unresolved cited work.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:26.840424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 66bf273c-1e06-4d56-afe4-6fd84053bc88 · outbound

This paper cites an unresolved cited work.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:26.707120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1558d73b-2462-4bef-ab43-9a2e4717d999 · outbound

This paper cites an unresolved cited work.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:26.566568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f5e688c0-7e52-45eb-873c-7744720a65c6 · outbound

This paper cites MLC-SLM Challenge: Multilingual conversational speech language model at interspeech 2025,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations MLC-SLM Challenge: Multilingual conversational speech language model at interspeech 2025,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:26.423917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0d096d98-faab-4ca7-889b-11ccfb0be2ef · outbound

This paper cites Mlc-slm baseline,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Mlc-slm baseline,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:26.307532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a032a453-4cde-4bb0-9a3a-b7328767e311 · outbound

This paper cites One model to rule them all ? towards end-to-end joint speaker diarization and speech recognition,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations One model to rule them all ? towards end-to-end joint speaker diarization and speech recognition,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:26.159257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ba6a276c-475e-4e45-ac1e-57f0e35844b8 · outbound

This paper cites Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:22.701392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be1a69f3-b89b-413c-8068-a96f57cc53e7 · outbound

This paper cites The Llama 3 Herd of Models.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:22.756454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4457049d-35be-438b-acd3-1c944c089540 · outbound

This paper cites Llama-3.2-3b-instruct,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Llama-3.2-3b-instruct,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:25.977996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0e0d6f22-d59f-48af-b2fb-9667a25e1f2c · outbound

This paper cites Llama-3.1-8b,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Llama-3.1-8b,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:25.772995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 00caef1b-0780-405b-80ee-7970997b23b5 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations LoRA: Low-Rank Adaptation of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:23.010828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8254148-5783-49b6-b7a7-bfba91d4b099 · outbound

This paper cites Robust Speech Recognition via Large-Scale Weak Supervision.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Robust Speech Recognition via Large-Scale Weak Supervision

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:23.077634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9de5b9ed-1ea3-4f79-b3e9-a20d81d1b7c9 · outbound

This paper cites Attention is all you need,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Attention is all you need,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:23.112256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2429ca22-968e-4162-89f7-72ac7fd86c1e · outbound

This paper cites Gaussian Error Linear Units (GELUs).

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Gaussian Error Linear Units (GELUs)

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:23.215615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94d9383e-01bb-490f-97ff-cdf718ed9599 · outbound

This paper cites Deep learning using rectified linear units (relu),.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Deep learning using rectified linear units (relu),

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:25.626964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8cdc420f-ec55-4185-b29f-0836110cb1f7 · outbound

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

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Cam++: A fast and efficient network for speaker verification using context- aware masking,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:24.809117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7034c702-516b-4d5c-927e-e5e5559d3b38 · outbound

This paper cites Layer normalization,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Layer normalization,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:25.398028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 486eb58d-5e5a-4076-bc2f-1ba72c2a48a1 · outbound

This paper cites Decoupled Weight Decay Regularization.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Decoupled Weight Decay Regularization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:24.055127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0b1c17c-01ba-4e8d-8fc3-0a7641dd45b7 · outbound

This paper cites Specaugment: A simple data augmentation method for automatic speech recognition,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Specaugment: A simple data augmentation method for automatic speech recognition,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:25.237377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fd896728-cf7c-4fe3-9ea2-445fea9238c8 · outbound

This paper cites U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:23.720920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76e558a2-1e79-47eb-b161-d34396e82d53 · outbound

This paper cites MeetEval: A toolkit for computation of word error rates for meeting transcription systems,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations MeetEval: A toolkit for computation of word error rates for meeting transcription systems,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:25.138961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 887ff142-7eac-477a-afcc-2dbf54c6ad69 · outbound

This paper cites Llama-3.2-1b-instruct,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Llama-3.2-1b-instruct,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:24.955834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6a1226b5-a830-44c5-bffa-5e91f6043196 · outbound

This paper cites Phi-4-multimodal-instruct: Lightweight open multimodal foundation model with text, im- age, and audio inputs,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Phi-4-multimodal-instruct: Lightweight open multimodal foundation model with text, im- age, and audio inputs,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:24.642017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5a18d2db-20f7-4068-8387-0cd374a02e8c · outbound

This paper cites Phi-4-multimodal-finetune-KO-speech: A ko- rean speech-to-text fine-tuned model based on phi-4 mul- timodal,.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Phi-4-multimodal-finetune-KO-speech: A ko- rean speech-to-text fine-tuned model based on phi-4 mul- timodal,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:42:24.464893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e9509a76-cff3-49d6-9ab8-ced3f31519b3 · outbound

This paper cites Layer Normalization.

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Layer Normalization

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:23.501469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e5df7ac-4f4a-4600-8efa-cbd1e3b62c98 · outbound

This paper cites Deep Learning using Rectified Linear Units (ReLU).

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations Deep Learning using Rectified Linear Units (ReLU)

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:23.349608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 972f97d3-9aa0-413e-9205-bbe5055e1865 · inbound