Paper Citation Record · LEDGER

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation

As of 8 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 1 inbound Pith citation observation for arXiv:2505.20606.

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

pith.paper-citation-record.v1
2505.20606 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:56:56.636821Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:56:54.638430Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T13:56:57.785085Z

Reference resolution

43 of 43 outbound references displayed

verified exact6
verified fuzzy16
unresolved19
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1a0279a9-3f9f-4903-99f0-5aaaacb4ecf7 · outbound

This paper cites an unresolved cited work.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:57:02.170344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8d83996d-c3ef-40d0-913b-73bfcc45fe97 · outbound

This paper cites an unresolved cited work.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:57:02.067797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 54f20529-a02e-4548-b991-f00dfb254308 · outbound

This paper cites an unresolved cited work.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:57:01.956952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2d199a2d-2659-4fad-93e4-3481cd909423 · outbound

This paper cites an unresolved cited work.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:57:01.788333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7e7d81fe-947a-4da8-aa87-290dbe8fef48 · outbound

This paper cites Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:56:57.859401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cabe68fa-e73e-4d8c-82fb-9efe9e8c9f09 · outbound

This paper cites an unresolved cited work.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:57:01.552188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cbaa0116-cf29-4e2e-a768-a6f343369d9f · outbound

This paper cites an unresolved cited work.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:57:01.345731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ba028c0f-89d5-410d-a976-2b65e51a68a9 · outbound

This paper cites Deep Speech: Scaling up end-to-end speech recognition.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Deep Speech: Scaling up end-to-end speech recognition

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:55.421526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44ef5d35-cd0f-4062-afcf-66c6ec165d72 · outbound

This paper cites In this section, we focus on acoustic data augmentation techniques and investigate their ef- fects on the robustness of the pre-trained ASR models.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation In this section, we focus on acoustic data augmentation techniques and investigate their ef- fects on the robustness of the pre-trained ASR models

Reference 9

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:56:57.704666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c603ae28-a860-428c-8cf8-641ba727deb4 · outbound

This paper cites When data sources are lim- ited, acoustic augmentations can significantly outperform exist- ing data augmentation methods on unseen speech.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation When data sources are lim- ited, acoustic augmentations can significantly outperform exist- ing data augmentation methods on unseen speech

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:57:01.013936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5d37df95-1f99-4f47-b8ae-994a436c9dc8 · outbound

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

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Robust Speech Recognition via Large-Scale Weak Supervision

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:55.026428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ebf554-82fe-49b7-abcc-42d6564375d7 · outbound

This paper cites Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:56:57.480429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 333cd5cc-1b12-4dfd-84ff-a0cd5e043820 · outbound

This paper cites Synthasr: Unlocking synthetic data for speech recognition,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Synthasr: Unlocking synthetic data for speech recognition,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:55.167614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b881408-475b-4499-9948-6255fb0937af · outbound

This paper cites On the effect of purely synthetic training data for different automatic speech recognition architectures,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation On the effect of purely synthetic training data for different automatic speech recognition architectures,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:57:00.873645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 73b0f32e-719a-480b-aacc-d3dc992d1dbe · outbound

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

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Specaugment: A simple data augmentation method for automatic speech recognition,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:55.292701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51e3dfa3-65e0-4929-b62c-45324a3383dd · outbound

This paper cites Specmix : A mixed sample data augmentation method for training with time-frequency do- main features,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Specmix : A mixed sample data augmentation method for training with time-frequency do- main features,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:57:00.705134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a07d7668-f1f0-4db8-a9d8-d350ef243d78 · outbound

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

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Lib- rispeech: An asr corpus based on public domain audio books,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:55.387341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a9f93f7-bbe5-4128-a8bc-b4ff75ed98a1 · outbound

This paper cites Adversarial audio synthesis,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Adversarial audio synthesis,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:56:59.383094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8b869c13-38fb-4e27-bc6c-d5f950df8075 · outbound

This paper cites Audio aug- mentation for speech recognition,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Audio aug- mentation for speech recognition,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:55.465809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 928197a7-e92a-4513-b6ff-6cf806406233 · outbound

This paper cites A study on data augmentation of reverberant speech for robust speech recognition,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation A study on data augmentation of reverberant speech for robust speech recognition,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:55.504875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a03fc3c-d6b3-4fdc-b057-3aec630b9bf0 · outbound

This paper cites Make more of your data: Minimal effort data augmentation for automatic speech recog- nition and translation,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Make more of your data: Minimal effort data augmentation for automatic speech recog- nition and translation,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:57:00.491754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ab50c095-0937-42b2-a9ac-02ce27793fa1 · outbound

This paper cites Specaugment++: A hidden space data augmentation method for acoustic scene classifica- tion,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Specaugment++: A hidden space data augmentation method for acoustic scene classifica- tion,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:57:00.263687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b49a376c-be19-40d6-b023-e51f76dd76c1 · outbound

This paper cites mixup: Beyond Empirical Risk Minimization.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation mixup: Beyond Empirical Risk Minimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:55.652123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f581be0-92d3-4860-acbc-42a83b7dbe74 · outbound

This paper cites Sapaugment: Learning a sample adaptive policy for data augmentation,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Sapaugment: Learning a sample adaptive policy for data augmentation,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:57:00.052668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ec2af8f9-279d-4b1e-8cfd-1076cc5cae48 · outbound

This paper cites G- augment: Searching for the meta-structure of data augmentation policies for asr,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation G- augment: Searching for the meta-structure of data augmentation policies for asr,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:56:59.786856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c0a8367b-8cb8-4fef-a8ee-29ec8325e25a · outbound

This paper cites Sample adaptive data augmentation with progressive scheduling.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Sample adaptive data augmentation with progressive scheduling

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:55.784699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 393fcbf2-e0df-49ab-a888-33ed3cb0738f · outbound

This paper cites Natural tts synthesis by condi- tioning wavenet on mel spectrogram predictions,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Natural tts synthesis by condi- tioning wavenet on mel spectrogram predictions,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:56:59.607480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 64c7b986-a8d9-42a5-9f62-d13e29d1863d · outbound

This paper cites Fasa: a flexible and automatic speech aligner for extracting high-quality aligned children speech data,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Fasa: a flexible and automatic speech aligner for extracting high-quality aligned children speech data,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:56:58.265363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2cef622d-22fc-4995-9b8f-0d57e215b6bf · outbound

This paper cites Kokoro-82m (revision d8b4fc7),.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Kokoro-82m (revision d8b4fc7),

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:56:59.197655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 60634783-6f84-4536-afc3-4779143341d1 · outbound

This paper cites Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:56:57.278482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fd4b739b-4213-4b68-a54c-ecd5b5438a87 · outbound

This paper cites Investigating the use of syn- thetic speech data for the analysis of spanish-accented english pronunciation patterns in asr,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Investigating the use of syn- thetic speech data for the analysis of spanish-accented english pronunciation patterns in asr,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:56:58.974493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 83eac2cc-6289-448c-bd85-1c47293234aa · outbound

This paper cites Asr data augmentation in low-resource settings using cross-lingual multi- speaker tts and cross-lingual voice conversion,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Asr data augmentation in low-resource settings using cross-lingual multi- speaker tts and cross-lingual voice conversion,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:56:58.779650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6afb2ec3-2a45-4332-a146-70c8f4593511 · outbound

This paper cites Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:56.189341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7b3fc1c-560d-47c7-81f5-4bb89e71b0f1 · outbound

This paper cites Dialog inpainting: Turning documents to dialogs,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Dialog inpainting: Turning documents to dialogs,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:56:58.509428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f794b98d-fc3e-42d1-ab34-7e0e353c2cee · outbound

This paper cites iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:56:57.078014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ffe792b9-1823-40a8-b57d-84b5f44a1e5a · outbound

This paper cites StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:56.300139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6135c121-0bd4-45b7-8f96-dcbbd0ae197e · outbound

This paper cites librosa/librosa: 0.10.2,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation librosa/librosa: 0.10.2,

Reference 37

Resolution: verified exact; doi, observed 2026-08-07T13:56:56.851938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c3bb1be4-d50f-4c56-a5be-6b4952483855 · outbound

This paper cites My science tutor (myst) – a large corpus of children’s conversational speech,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation My science tutor (myst) – a large corpus of children’s conversational speech,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:56:58.044553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a3ffe455-f07f-4c73-8f7a-8cc51438d76a · outbound

This paper cites L2-arctic: A non- native english speech corpus,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation L2-arctic: A non- native english speech corpus,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:56.573567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7faa8a5-cd23-4236-9c0c-87ffab7ce201 · outbound

This paper cites Phonological differences between received pronunciation and standard scottish english,.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation Phonological differences between received pronunciation and standard scottish english,

Reference 43

Resolution: verified exact; doi, observed 2026-08-07T13:56:56.786888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ab20909a-9d09-49d6-83f1-bf6560fc70a7 · outbound

This paper cites All experiments are conducted on a server with 4 A6000 GPUs.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation All experiments are conducted on a server with 4 A6000 GPUs

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:57:01.141473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8519f050-3ef1-441d-8650-717624f44814 · outbound

This paper cites My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speech.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation My Science Tutor (MyST) -- A Large Corpus of Children's Conversational Speech

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T13:56:56.534182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c5729db-937e-4474-888d-42ba49be999c · outbound

This paper cites FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Data.

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Data

Reference 2024

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T13:56:56.964789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 7e7d81fe-947a-4da8-aa87-290dbe8fef48 · inbound