Paper Citation Record · LEDGER

Robust fine-tuning of speech recognition models via model merging: application to disordered speech

As of 9 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2505.20477.

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

pith.paper-citation-record.v1
2505.20477 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:58:39.430678Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:58:36.497364Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T13:58:39.905074Z

Reference resolution

40 of 40 outbound references displayed

verified exact3
verified fuzzy27
unresolved9
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c3c5ab76-7f16-40e9-9505-94ffbcf48f05 · outbound

This paper cites Robust fine-tuning of speech recognition models via model merging: application to disordered speech.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Robust fine-tuning of speech recognition models via model merging: application to disordered speech

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:58:39.989618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5cf83cec-96ec-4530-ad6c-0e736d380ced · outbound

This paper cites an unresolved cited work.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:58:44.379234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fcdd9eb7-6779-4755-9af2-80d78d563085 · outbound

This paper cites Model Merging Model merging strategies have demonstrated performance im- provements in out-of-distribution predictions for vision models.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Model Merging Model merging strategies have demonstrated performance im- provements in out-of-distribution predictions for vision models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:44.198113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1573dd1d-ad04-4fd0-8a97-77af9b78e9ef · outbound

This paper cites As shown in Fig- ure 1, MAST outperformed standard fine-tuning, demonstrat- ing the benefits of weight averaging along a single optimization 2https://github.com/openai/whisper path.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech As shown in Fig- ure 1, MAST outperformed standard fine-tuning, demonstrat- ing the benefits of weight averaging along a single optimization 2https://github.com/openai/whisper path

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:58:43.695280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4ec3c2cb-b1c3-4994-9470-90fcdcf346be · outbound

This paper cites Our findings demonstrate that model merg- ing, particularly selective merging across multiple trajectories, significantly improves WER compared to traditional fine-tuning methods.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Our findings demonstrate that model merg- ing, particularly selective merging across multiple trajectories, significantly improves WER compared to traditional fine-tuning methods

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:43.516661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fc42ede6-a46f-490a-9fd8-cc22338b4c4e · outbound

This paper cites Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:58:37.410101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1c7351d-7109-4664-a81a-e8321c7da146 · outbound

This paper cites Whisper-at: Noise-robust automatic speech recognizers are also strong general audio event taggers,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Whisper-at: Noise-robust automatic speech recognizers are also strong general audio event taggers,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:42.734222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dce8a5d4-4827-4209-b163-dc06c704b91b · outbound

This paper cites Data determines distributional robustness in contrastive language image pre-training (clip),.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Data determines distributional robustness in contrastive language image pre-training (clip),

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:43.316824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fe33aea0-abce-4830-8250-0e4e86223637 · outbound

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

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:58:37.144885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dabfa7a-8353-49ce-8a09-c264d92a9e39 · outbound

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

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Wavlm: Large-scale self- supervised pre-training for full stack speech processing,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:58:37.207220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 435120b0-1928-4941-9f93-941e2e7c066a · outbound

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

Robust fine-tuning of speech recognition models via model merging: application to disordered speech wav2vec 2.0: A framework for self-supervised learning of speech representa- tions,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:43.087943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3ab48af0-e95a-49cb-b69c-427e562d3d49 · outbound

This paper cites Towards better domain adaptation for self-supervised models: A case study of child asr,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Towards better domain adaptation for self-supervised models: A case study of child asr,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:42.913107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 39fb60f9-26e2-4a09-8881-264595132dd8 · outbound

This paper cites Robust speech recognition via large-scale weak supervision,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Robust speech recognition via large-scale weak supervision,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:58:37.917347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a0ec55-7ccf-4fed-a867-bdddf0573317 · outbound

This paper cites Community-supported shared infrastructure in support of speech accessibility,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Community-supported shared infrastructure in support of speech accessibility,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:41.935950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4a5df618-7d47-4f7f-9fcc-4a9847e82add · outbound

This paper cites Improving domain generalization in speech emotion recognition with whisper,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Improving domain generalization in speech emotion recognition with whisper,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:42.525659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 082a6d5a-bdb4-4ad2-a31b-34c262e0502d · outbound

This paper cites Trans- ferring speech-generic and depression-specific knowledge for alzheimer’s disease detection,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Trans- ferring speech-generic and depression-specific knowledge for alzheimer’s disease detection,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:42.379795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8dedef92-abff-4ff7-9286-1a3ea4ad7bcc · outbound

This paper cites Automated speech analysis for risk detection of depression, anxiety, insomnia, and fatigue: Algorithm development and validation study,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Automated speech analysis for risk detection of depression, anxiety, insomnia, and fatigue: Algorithm development and validation study,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:42.218147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8f51eef-a3a4-417b-bf2a-948aac0ad2cb · outbound

This paper cites To- wards inclusive automatic speech recognition,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech To- wards inclusive automatic speech recognition,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:58:37.759356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3549fa43-c635-492f-a681-20d0b89989b3 · outbound

This paper cites Disordered speech data collection: Lessons learned at 1 million utterances from project euphonia.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Disordered speech data collection: Lessons learned at 1 million utterances from project euphonia

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:42.055757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a32b1857-fffa-4ec6-9ccf-913267e79696 · outbound

This paper cites Thus, we now explore various model merging approaches to enhance Whisper.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Thus, we now explore various model merging approaches to enhance Whisper

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:44.052819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f914957f-384a-484d-94ef-228ecfa66489 · outbound

This paper cites Diverse weight averaging for out-of- distribution generalization,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Diverse weight averaging for out-of- distribution generalization,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:41.066050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 316514ea-6a16-4833-b552-1d197e604fe3 · outbound

This paper cites Investigating self- supervised pretraining frameworks for pathological speech recog- nition,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Investigating self- supervised pretraining frameworks for pathological speech recog- nition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:41.813776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ae5ecf29-93e1-4713-9058-0e10f8adb8cb · outbound

This paper cites Training data augmentation for dysarthric automatic speech recognition by text- to-dysarthric-speech synthesis,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Training data augmentation for dysarthric automatic speech recognition by text- to-dysarthric-speech synthesis,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:41.664938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 21cf4fe9-946c-4846-b966-0bc9ab268720 · outbound

This paper cites Fine-tuning strategies for dutch dysarthric speech recog- nition: Evaluating the impact of healthy, disease-specific, and speaker-specific data,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Fine-tuning strategies for dutch dysarthric speech recog- nition: Evaluating the impact of healthy, disease-specific, and speaker-specific data,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:41.519735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a7d2189e-6303-4696-9da0-2b533972ff46 · outbound

This paper cites Averaging weights leads to wider optima and better generaliza- tion,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Averaging weights leads to wider optima and better generaliza- tion,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:41.417391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6697eb9e-7655-4aa1-94fb-c0b1f67f9d1c · outbound

This paper cites Model soups: averaging weights of multi- ple fine-tuned models improves accuracy without increasing in- ference time,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Model soups: averaging weights of multi- ple fine-tuned models improves accuracy without increasing in- ference time,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:41.314620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ccd85e6d-a933-46ef-a96c-349166498234 · outbound

This paper cites Formally, we denote by θ0,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Formally, we denote by θ0,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:43.872697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7388b8d9-45eb-44cf-abf3-51e8de034a20 · outbound

This paper cites Robust fine-tuning of zero-shot models,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Robust fine-tuning of zero-shot models,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:41.194739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d9e4af42-5814-4392-9277-64ca6392fc38 · outbound

This paper cites Learning and trans- ferring mid-level image representations using convolutional neu- ral networks,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Learning and trans- ferring mid-level image representations using convolutional neu- ral networks,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:40.943665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 044900b1-b444-4a00-82d4-efa4f58ba43f · outbound

This paper cites Selective Attention Merging for low resource tasks: A case study of Child ASR.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Selective Attention Merging for low resource tasks: A case study of Child ASR

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:58:39.789031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 32570c40-316a-42a7-8510-420e90eb36cf · outbound

This paper cites BERTScore: Evaluating Text Generation with BERT.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech BERTScore: Evaluating Text Generation with BERT

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:58:38.742997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48751630-1b99-4aa2-b8b2-d8884e2d7c98 · outbound

This paper cites MENLI: Robust Evaluation Metrics from Natural Language Inference.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech MENLI: Robust Evaluation Metrics from Natural Language Inference

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:58:39.621087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dece3421-27a0-4901-885d-861f27f79ab0 · outbound

This paper cites Rewarded soups: towards pareto- optimal alignment by interpolating weights fine-tuned on diverse rewards,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Rewarded soups: towards pareto- optimal alignment by interpolating weights fine-tuned on diverse rewards,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:40.811493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 25949168-de5b-4f7b-881b-239fe20cfa5e · outbound

This paper cites Robust speech recognition via large-scale weak su- pervision,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Robust speech recognition via large-scale weak su- pervision,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:40.664162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3605959a-d8da-46f0-a06a-91f207a4cfe3 · outbound

This paper cites Transform- ers: State-of-the-art natural language processing,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Transform- ers: State-of-the-art natural language processing,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:40.533854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d1915e1b-4e45-4c48-b092-df32f1ea8b83 · outbound

This paper cites Specaugment on large scale datasets,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Specaugment on large scale datasets,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:40.408297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation feffd138-e991-4ac4-b5d2-65c66bae5469 · outbound

This paper cites Linear mode connectivity and the lottery ticket hypothesis,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Linear mode connectivity and the lottery ticket hypothesis,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:40.295870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 87b304ce-43b7-41b0-adc3-bca2fa89fdeb · outbound

This paper cites The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:58:39.275719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fa57d73-72ca-406a-b633-d38e7d24b9b8 · outbound

This paper cites What Matters for Model Merging at Scale?.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech What Matters for Model Merging at Scale?

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:58:39.345675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f6bd1dc-eda1-47ee-8725-ee4b19342d2e · outbound

This paper cites Arcee’s MergeKit: A toolkit for merging large language mod- els,.

Robust fine-tuning of speech recognition models via model merging: application to disordered speech Arcee’s MergeKit: A toolkit for merging large language mod- els,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:58:40.116603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation c3c5ab76-7f16-40e9-9505-94ffbcf48f05 · inbound