Paper Citation Record · LEDGER

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation

As of 18 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2505.13338.

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

pith.paper-citation-record.v1
2505.13338 v2

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:17:33.475816Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:17:33.349929Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T20:17:33.661042Z

Reference resolution

40 of 40 outbound references displayed

verified exact1
verified fuzzy20
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation df2a375e-9c0e-41e4-8847-09a411b397de · outbound

This paper cites Recent speech-LLMs, such as GPT-4 [1], Qwen-audio [2, 3], SALMONN [4], and MERaLiON-AudioLLM [5, 6], have demonstrated remarkable performance in handling speech-based tasks.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Recent speech-LLMs, such as GPT-4 [1], Qwen-audio [2, 3], SALMONN [4], and MERaLiON-AudioLLM [5, 6], have demonstrated remarkable performance in handling speech-based tasks

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.932117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5b3e0b13-e110-4c94-b1d6-097889e13798 · outbound

This paper cites Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:17:33.666296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 44a15b1d-4201-4976-9b78-db81f5b07cdf · outbound

This paper cites What is the content in the audio from the text transcript?.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation What is the content in the audio from the text transcript?

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.921636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7c3ff951-5a41-4ef3-b9a1-8ddfa4e8a78d · outbound

This paper cites an unresolved cited work.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:17:33.911818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d1a5bcd2-cc09-493b-a09b-067d749df2e0 · outbound

This paper cites an unresolved cited work.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:17:33.900926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c8563fb2-e5da-44cf-bd61-a3d7a911e0e5 · outbound

This paper cites Our framework con- sists of pseudo paralinguistic label-based data condensation and LLM-based CPQA generation.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Our framework con- sists of pseudo paralinguistic label-based data condensation and LLM-based CPQA generation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.364103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 257f1e2b-b648-44d7-81eb-7239a32a713c · outbound

This paper cites an unresolved cited work.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:17:33.890556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a8c59dad-2984-4c64-b67b-03064de6c960 · outbound

This paper cites GPT-4 Technical Report.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation GPT-4 Technical Report

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.371023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4e56222-2487-41b0-b0f7-c939eed97885 · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.374448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ec7c9d2-eead-4631-8149-034f16ba74cb · outbound

This paper cites Qwen2-Audio Technical Report.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Qwen2-Audio Technical Report

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.377815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c02a3a55-2109-418b-a084-029faeb96724 · outbound

This paper cites SALMONN: Towards Generic Hearing Abilities for Large Language Models.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation SALMONN: Towards Generic Hearing Abilities for Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.380885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b47227b3-c8cf-413e-916b-6b0f82b780df · outbound

This paper cites MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.384225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79ba7230-e884-473a-bbec-18385fee75db · outbound

This paper cites MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.387816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1a5cc0e-951c-4a5a-92d5-eb332a8eccf7 · outbound

This paper cites BLSP-Emo: Towards Empathetic Large Speech-Language Models.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation BLSP-Emo: Towards Empathetic Large Speech-Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.391551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcac46d7-5359-459f-a598-dae8ec7ca2c0 · outbound

This paper cites AudioPaLM: A Large Language Model That Can Speak and Listen.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation AudioPaLM: A Large Language Model That Can Speak and Listen

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.394954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5e1c955-edc6-462f-bfaf-0e48780e59b4 · outbound

This paper cites LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.399189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cd1ed08-992a-426b-a7d7-721c2ccef8fc · outbound

This paper cites Advancing large lan- guage models to capture varied speaking styles and respond prop- erly in spoken conversations,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Advancing large lan- guage models to capture varied speaking styles and respond prop- erly in spoken conversations,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.880417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation adf22b68-6130-4741-bcf3-9340321f1889 · outbound

This paper cites BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.405082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb7090e5-9f39-421b-b88a-f8e163372e9a · outbound

This paper cites Paralinguistics-aware speech- empowered large language models for natural conversation,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Paralinguistics-aware speech- empowered large language models for natural conversation,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.868245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6a3ad9af-4b75-44f7-8891-2fe02c825a7a · outbound

This paper cites Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.412848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cad0500-702b-4260-805d-dfb6d0be4ad9 · outbound

This paper cites AudioBench: A universal benchmark for audio large language models,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation AudioBench: A universal benchmark for audio large language models,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.858006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 40ca13f3-6ee6-43b9-96a4-2eb4d6e4422c · outbound

This paper cites Dynamic-superb: To- wards a dynamic, collaborative, and comprehensive instruction- tuning benchmark for speech,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Dynamic-superb: To- wards a dynamic, collaborative, and comprehensive instruction- tuning benchmark for speech,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.847956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d7cda837-7c18-4c6c-822a-2c129c3e9a70 · outbound

This paper cites AIR-bench: Benchmark- ing large audio-language models via generative comprehension,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation AIR-bench: Benchmark- ing large audio-language models via generative comprehension,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.837167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b88e64c0-7555-4a25-9946-fbe3044dbbf5 · outbound

This paper cites Listen, think, and understand,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Listen, think, and understand,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.425641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c5cccfd-59b3-42fd-aa6f-9f515ba723aa · outbound

This paper cites MMAU: A mas- sive multi-task audio understanding and reasoning benchmark,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation MMAU: A mas- sive multi-task audio understanding and reasoning benchmark,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.818914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8965e6db-6080-48ac-804c-ad5240d7ae40 · outbound

This paper cites IEMOCAP: interactive emotional dyadic motion capture database,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation IEMOCAP: interactive emotional dyadic motion capture database,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.807231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d012c2ef-7d75-4efe-8248-b05d1ac94826 · outbound

This paper cites MELD: A multimodal multi-party dataset for emo- tion recognition in conversations,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation MELD: A multimodal multi-party dataset for emo- tion recognition in conversations,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.797163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a129374a-a85b-4739-941c-7dd619b5a975 · outbound

This paper cites What’s basic about basic emotions?.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation What’s basic about basic emotions?

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.785652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 85b7fc7a-0eb6-4d69-b73d-087401a787b0 · outbound

This paper cites Theories of emotion,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Theories of emotion,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.775706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2418c4d2-380d-4b51-8d7d-6902ebc7b32e · outbound

This paper cites EmoBox: Multilingual multi-corpus speech emotion recognition toolkit and benchmark,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation EmoBox: Multilingual multi-corpus speech emotion recognition toolkit and benchmark,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.765848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8bc8255e-2381-4b4b-b1f3-04acb1b2d49b · outbound

This paper cites Evidence for a three-factor the- ory of emotions,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Evidence for a three-factor the- ory of emotions,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.755021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5fc62db6-16d6-42cf-accd-f389cbbbabf2 · outbound

This paper cites Goemotions: A dataset of fine-grained emo- tions,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Goemotions: A dataset of fine-grained emo- tions,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.745284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 90ead142-5439-4f7a-bcd5-0cfd198265af · outbound

This paper cites emotion2vec: Self-supervised pre-training for speech emotion representation,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation emotion2vec: Self-supervised pre-training for speech emotion representation,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.734700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5d0fc0a3-4a9a-4c29-836a-9cf4ef2e8d60 · outbound

This paper cites Dawn of the trans- former era in speech emotion recognition: Closing the valence gap,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Dawn of the trans- former era in speech emotion recognition: Closing the valence gap,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.457390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 481c58b7-2554-485f-b02e-aeb833128bff · outbound

This paper cites Building naturalistic emotionally bal- anced speech corpus by retrievingemotional speech from existing podcast recordings,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Building naturalistic emotionally bal- anced speech corpus by retrievingemotional speech from existing podcast recordings,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.718410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3cbdafd9-b7a6-4a4b-ac0c-3a9ef94c2ea6 · outbound

This paper cites WavLM: Large-scale self- supervised pre-training for full stack speech processing,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation WavLM: Large-scale self- supervised pre-training for full stack speech processing,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.463514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26111fcc-14e8-4c9d-8386-3f5270689267 · outbound

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

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation Ecapa-tdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.701994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 35d844f6-a36d-41b0-a4a0-63ae8a49271c · outbound

This paper cites V oxCeleb2: Deep speaker recognition,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation V oxCeleb2: Deep speaker recognition,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:17:33.469808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a6e8142-01c7-4b17-8889-90906e41acac · outbound

This paper cites WhisperX: Time- accurate speech transcription of long-form audio,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation WhisperX: Time- accurate speech transcription of long-form audio,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.686760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e96a01a8-e897-4f96-8521-8b45b64ba23a · outbound

This paper cites The Llama 3 herd of models,.

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation The Llama 3 herd of models,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:17:33.676651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 5b3e0b13-e110-4c94-b1d6-097889e13798 · inbound