Paper Citation Record · LEDGER

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge

As of 21 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2505.24493.

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

pith.paper-citation-record.v1
2505.24493 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:27:30.556529Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:27:26.864720Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T12:27:31.120281Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy20
unresolved17
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 402ac5de-66b2-4199-bf35-69f4371c4609 · outbound

This paper cites MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:27:31.225846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0a6528c0-cd32-4f50-9cfd-fd596d54520c · outbound

This paper cites 1st Customer.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge 1st Customer

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:34.805142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 633642c8-a18f-4dbf-bec1-c711c7d9406c · outbound

This paper cites Emo Prediction.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Emo Prediction

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:34.608199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 26ad3144-fb9d-4890-a481-7c9e6c2b4a38 · outbound

This paper cites Subjective Experiment To assess the emotion annotation quality, we invited 20 par- ticipants, comprising 11 males and 9 females to conduct a Mean Opinion Score (MOS) experiment.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Subjective Experiment To assess the emotion annotation quality, we invited 20 par- ticipants, comprising 11 males and 9 females to conduct a Mean Opinion Score (MOS) experiment

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T12:27:31.044694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 77a5abfc-b9ba-4998-a0a1-536b1eb404c4 · outbound

This paper cites Performance The overall MOS result is shown in Fig.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Performance The overall MOS result is shown in Fig

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:34.513190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2870d4d2-c87c-4e41-b056-05e6767a9f00 · outbound

This paper cites To achieve this, we developed a prompting strategy incorporating cross-validation and CoT rea- soning to ensure consistent and accurate annotations.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge To achieve this, we developed a prompting strategy incorporating cross-validation and CoT rea- soning to ensure consistent and accurate annotations

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:34.373866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 40bc5abf-dbd0-4a94-9992-2aad67ef0218 · outbound

This paper cites Schuller is also with the Munich Data Science Insti- tute and the Konrad Zuse School of Excellence in Reliable AI, both in Munich, Germany.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Schuller is also with the Munich Data Science Insti- tute and the Konrad Zuse School of Excellence in Reliable AI, both in Munich, Germany

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:34.233138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 67387979-9e87-4696-b7c9-e968f89b0446 · outbound

This paper cites Be- yond deep learning: Charting the next frontiers of affective com- puting,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Be- yond deep learning: Charting the next frontiers of affective com- puting,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:34.043674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3f2e4355-2c90-4e2f-b94c-a6a4d105c234 · outbound

This paper cites En- hancing emotional text-to-speech controllability with natural lan- guage guidance through contrastive learning and diffusion mod- els,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge En- hancing emotional text-to-speech controllability with natural lan- guage guidance through contrastive learning and diffusion mod- els,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:33.903281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c5e9f569-d767-4100-bfc5-57040ed1b31d · outbound

This paper cites Emotion recognition in context,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Emotion recognition in context,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:33.725487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation feafe0e5-f059-4a73-84ab-a7cc6783b03b · outbound

This paper cites Contextual Emotion Recognition using Large Vision Language Models.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Contextual Emotion Recognition using Large Vision Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:27.873897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8eff7a5-9bcd-4917-a2c1-47ab01bb0441 · outbound

This paper cites The human in emotion recognition on social media: Attitudes, outcomes, risks,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge The human in emotion recognition on social media: Attitudes, outcomes, risks,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:33.548809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e6423b5b-6bd8-4dc8-96b2-940c3cc04980 · outbound

This paper cites Language models are unsupervised multitask learners,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Language models are unsupervised multitask learners,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:28.088535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4c1fadf-d6eb-4ee0-b898-87f0b163e5a7 · outbound

This paper cites Language Models are Few-Shot Learners.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Language Models are Few-Shot Learners

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:28.164916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 507770af-6dac-4c0d-b692-82ef45a2283f · outbound

This paper cites GPT-4o System Card.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge GPT-4o System Card

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:28.249407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e35159-b0a7-4c28-9c50-f89fddd93f71 · outbound

This paper cites Large Language Models for Data Annotation and Synthesis: A Survey.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Large Language Models for Data Annotation and Synthesis: A Survey

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:28.359993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b00d479-fa07-4bc1-8d12-dd421f3e78cf · outbound

This paper cites Chatgpt vs. human annotators: A comprehen- sive analysis of chatgpt for text annotation,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Chatgpt vs. human annotators: A comprehen- sive analysis of chatgpt for text annotation,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:33.412896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2b63ef89-f5eb-45c1-9b2a-d360e614254f · outbound

This paper cites Chatgpt outperforms crowd workers for text-annotation tasks,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Chatgpt outperforms crowd workers for text-annotation tasks,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:33.259232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bc585383-0a91-4d08-9cc7-15eb89bb6556 · outbound

This paper cites Wavcaps: A chatgpt-assisted weakly- labelled audio captioning dataset for audio-language multimodal research,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Wavcaps: A chatgpt-assisted weakly- labelled audio captioning dataset for audio-language multimodal research,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:33.108845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a3d040bf-46f1-4e6d-bd62-7a2bc5540e12 · outbound

This paper cites Pengi: An audio language model for audio tasks,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Pengi: An audio language model for audio tasks,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:28.671061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb199048-d0c0-410e-a418-3b9cbe7bbb88 · outbound

This paper cites Secap: Speech emotion captioning with large language model,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Secap: Speech emotion captioning with large language model,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:32.890406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 829657dd-f225-475a-a7ac-269940d2f011 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge LLaMA: Open and Efficient Foundation Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:28.833637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb9d5785-08b4-4876-b801-17776bf9b817 · outbound

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

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Meld: A multimodal multi-party dataset for emo- tion recognition in conversations,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:32.684728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e304351d-024f-49df-a304-ea7058bb1faa · outbound

This paper cites On the time course of vocal emotion recognition,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge On the time course of vocal emotion recognition,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:32.534749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 81739cf6-dc75-4887-9ef3-f7b436edad95 · outbound

This paper cites Applying tdnn architectures for an- alyzing duration dependencies on speech emotion recognition.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Applying tdnn architectures for an- alyzing duration dependencies on speech emotion recognition

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:32.234416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dd452cb9-5977-497a-9524-dcdbe58347ed · outbound

This paper cites A wide evaluation of chatgpt on affective computing tasks,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge A wide evaluation of chatgpt on affective computing tasks,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:32.062542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8a311e23-6e8a-4094-aeec-2a6c6432be05 · outbound

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

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:29.295963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64cdf607-ff54-4605-a33a-0040025a012e · outbound

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

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Dawn of the trans- former era in speech emotion recognition: closing the valence gap,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:29.431282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0c74c29-d9fe-4bd8-abe6-0afdd43d52d7 · outbound

This paper cites Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:29.512545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dd3754d-f5d6-4243-b857-115f071b1fed · outbound

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

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Wavlm: Large-scale self- supervised pre-training for full stack speech processing,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:29.656517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58958196-2d1a-4589-9851-37059db372d5 · outbound

This paper cites Iemocap: Interactive emotional dyadic motion capture database,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Iemocap: Interactive emotional dyadic motion capture database,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:29.800246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77085dc2-383e-455c-b349-9bcb8a4a2a87 · outbound

This paper cites Toronto emotional speech set (tess).

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Toronto emotional speech set (tess)

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:29.942112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5a16bbb-10cf-4525-9873-a9418b6712ab · outbound

This paper cites The ryerson audio-visual database of emotional speech and song (ravdess): A dynamic, multimodal set of facial and vocal expressions in north american english,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge The ryerson audio-visual database of emotional speech and song (ravdess): A dynamic, multimodal set of facial and vocal expressions in north american english,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:30.046700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66577d96-c517-4924-aeb0-82a1de589378 · outbound

This paper cites Crema-d: Crowd-sourced emotional multimodal actors dataset,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Crema-d: Crowd-sourced emotional multimodal actors dataset,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:30.136880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35b71e7-64cb-4d7c-9fe7-cb23a372826d · outbound

This paper cites EMO-SUPERB: An In-depth Look at Speech Emotion Recognition.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge EMO-SUPERB: An In-depth Look at Speech Emotion Recognition

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:30.198470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd2260ac-bae1-4883-9ce6-16fcdbcefecc · outbound

This paper cites Paraclap– towards a general language-audio model for computational par- alinguistic tasks,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge Paraclap– towards a general language-audio model for computational par- alinguistic tasks,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:31.857628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a0867d04-8d09-4afa-88d6-ba04896c76f8 · outbound

This paper cites The geneva minimalistic acoustic parameter set (gemaps) for voice research and affective computing,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge The geneva minimalistic acoustic parameter set (gemaps) for voice research and affective computing,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:27:30.409565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75f7473e-3a93-4c5f-b694-1ce0eeedf5b5 · outbound

This paper cites openSMILE: the Munich versatile and fast open-source audio feature extractor,.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge openSMILE: the Munich versatile and fast open-source audio feature extractor,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:31.684716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d99fd321-fc6d-4b52-aa62-e1f19f317c61 · outbound

This paper cites How do we describe other people from voices and faces?.

MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge How do we describe other people from voices and faces?

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:27:31.467360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 402ac5de-66b2-4199-bf35-69f4371c4609 · inbound