Paper Citation Record · LEDGER

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs

As of 7 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2604.08384.

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

pith.paper-citation-record.v1
2604.08384 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T17:17:56.737611Z

measured 34 of 34 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T17:17:56.737611Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-11T07:06:12.250682Z

Reference resolution

33 of 33 outbound references displayed

verified exact16
verified fuzzy12
unresolved3
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cc4fc86a-6ca9-4141-8abf-edde5dbb542c · outbound

This paper cites an unresolved cited work.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-05-17T11:09:29.371593Z

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 5fa10839-6a22-4b5c-9837-9e2669920d78 · outbound

This paper cites TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-11T07:06:12.315956Z

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 74106f46-641c-49d6-a253-66edb0e97806 · outbound

This paper cites an unresolved cited work.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-05-17T11:09:29.363488Z

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 c3794b6a-e30c-44ca-86ee-b9b4bcf7c907 · outbound

This paper cites generalization, and (ii) low-resource domain adaptation.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs generalization, and (ii) low-resource domain adaptation

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.367876Z

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 fee919b0-c359-4bcd-ba00-e0deeb49824a · outbound

This paper cites Table 2 probes whether simulated posteriors improve CTC-style alignment and cross-domain generalization without audio training.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Table 2 probes whether simulated posteriors improve CTC-style alignment and cross-domain generalization without audio training

Reference 5

Resolution: malformed identifier; raw_fallback, observed 2026-05-17T11:09:29.383357Z

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 bbd588e3-8d3c-41d1-8ff0-5393aef3f9a2 · outbound

This paper cites By generat- ing pseudo posteriors that better match acoustic CTC behavior, TASU2 provides stronger alignment signals for speech foun- dation models and Speech LLMs.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs By generat- ing pseudo posteriors that better match acoustic CTC behavior, TASU2 provides stronger alignment signals for speech foun- dation models and Speech LLMs

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.379732Z

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 642e6e31-b0ae-40f5-aef2-2786b3dab254 · outbound

This paper cites an unresolved cited work.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-05-17T11:09:29.374952Z

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 50287b34-59aa-4b99-86d6-2457e0bd1d62 · outbound

This paper cites A survey on speech large language models for understanding.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs A survey on speech large language models for understanding

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-10T17:20:38.428745Z

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 949a17d7-c4ae-4029-9c1d-36febd688001 · outbound

This paper cites On the landscape of spoken language models: A comprehensive survey.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs On the landscape of spoken language models: A comprehensive survey

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.386862Z

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 fc22db11-27fe-4f24-b9ed-19c7e66819e5 · outbound

This paper cites On The Landscape of Spoken Language Models: A Comprehensive Survey.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs On The Landscape of Spoken Language Models: A Comprehensive Survey

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T07:06:11.637295Z

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 1062955e-4f00-4601-908f-89f2e8c2c067 · outbound

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

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Robust Speech Recognition via Large-Scale Weak Supervision

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-11T07:06:11.965151Z

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 6553157c-282b-412f-b2e7-38c2efd85f8a · outbound

This paper cites Tasu: Text-only alignment for speech understanding.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Tasu: Text-only alignment for speech understanding

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.393553Z

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 84555d19-1ebf-440c-ac4a-79e026463336 · outbound

This paper cites Available: https://arxiv.org/abs/2511.03310.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Available: https://arxiv.org/abs/2511.03310

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:12.046496Z

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 517bb2a6-80bf-4895-8464-a4e1c67de9e3 · outbound

This paper cites LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:13.016146Z

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 be4cee44-e4c1-4c69-80ac-143e4e0fd0b8 · outbound

This paper cites Alignformer: Modality matching can achieve better zero-shot instruction- following speech-llm.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Alignformer: Modality matching can achieve better zero-shot instruction- following speech-llm

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.390153Z

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 7d95f8e0-c68c-4796-9555-73529d98518f · outbound

This paper cites Improving automatic speech recogni- tion performance for low-resource languages with self-supervised models.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Improving automatic speech recogni- tion performance for low-resource languages with self-supervised models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.400514Z

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 8aeb3fb0-c43c-4e90-b2aa-2687762be0b7 · outbound

This paper cites Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:12.516013Z

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 5cfe32ca-4174-4ec7-be4c-c9739f90a2aa · outbound

This paper cites Text-only adaptation in llm- based asr through text denoising.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Text-only adaptation in llm- based asr through text denoising

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:12.846187Z

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 bf116189-af5a-4d08-b05e-5ea15a88e8f8 · outbound

This paper cites Zero-shot domain-sensitive speech recognition with prompt- conditioning fine-tuning.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Zero-shot domain-sensitive speech recognition with prompt- conditioning fine-tuning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.409985Z

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 9bf6f57b-42c7-4eae-a05b-d5849a2a86d5 · outbound

This paper cites Low-resource domain adaptation for speech LLMs via text-only fine-tuning.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Low-resource domain adaptation for speech LLMs via text-only fine-tuning

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:12.342267Z

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 d6203fe9-a089-4b1c-af78-4bfc4caa93e2 · outbound

This paper cites ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:12.245913Z

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 2ad73b84-a0ae-443b-8cc5-5177a6921828 · outbound

This paper cites Blank Collapse: Compressing CTC emission for the faster decoding.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Blank Collapse: Compressing CTC emission for the faster decoding

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:12.669175Z

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 11922a35-06ec-4a42-bb1f-ff000f0bd364 · outbound

This paper cites Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:12.157812Z

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 edf43090-ebe6-410b-86d2-eba6549bf601 · outbound

This paper cites Phone synchronous decod- ing with ctc lattice.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Phone synchronous decod- ing with ctc lattice

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.407022Z

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 b2443b6c-f14d-4544-9bb3-07f72366e253 · outbound

This paper cites Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:11.728775Z

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 d677edc5-aa76-4171-9e60-5c81fe771d2c · outbound

This paper cites FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:12.756590Z

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 cb570388-3612-4b3d-b789-1a7126c3d789 · outbound

This paper cites Qwen2.5 Technical Report.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Qwen2.5 Technical Report

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-11T07:06:12.549556Z

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 395c7da2-5f42-4460-a121-a390e9e2af37 · outbound

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

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Lib- rispeech: An asr corpus based on public domain audio books

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.413642Z

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 3839cacb-3955-4874-a7fd-05f49eb707ac · outbound

This paper cites Medical speech, transcription, and intent.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Medical speech, transcription, and intent

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.396916Z

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 dd6adfa2-b408-445b-ac9b-1fbf2a327788 · outbound

This paper cites Hernandez, V.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Hernandez, V

Reference 30

Resolution: verified exact; doi, observed 2026-05-10T17:20:38.430409Z

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 9932684a-9e52-4243-a4eb-11d3dd24930b · outbound

This paper cites Slidespeech: A large-scale slide-enriched audio-visual corpus.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs Slidespeech: A large-scale slide-enriched audio-visual corpus

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.403803Z

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 2ef514e5-477f-4d03-b87e-86d2acf49887 · outbound

This paper cites SlideSpeech: A Large-Scale Slide-Enriched Audio-Visual Corpus.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs SlideSpeech: A Large-Scale Slide-Enriched Audio-Visual Corpus

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:06:11.846015Z

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 28942c7b-e034-45e0-a801-8b630621a7f5 · outbound

This paper cites CoVoST2 and massively multilingual speech-to- text translation.

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs CoVoST2 and massively multilingual speech-to- text translation

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T11:09:29.416992Z

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 5fa10839-6a22-4b5c-9837-9e2669920d78 · inbound