Paper Citation Record · LEDGER

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition

As of 10 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2601.19919.

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

pith.paper-citation-record.v1
2601.19919 v2

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T12:01:01.414371Z

measured 40 of 40 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 2026-08-03T12:00:57.108795Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy0
unresolved38
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 49609f18-4257-42b3-b0aa-914a023085e7 · outbound

This paper cites In addition, with the rapid advancement of hardware, deep learning (DL)-based ASR is gaining more attention [3].

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition In addition, with the rapid advancement of hardware, deep learning (DL)-based ASR is gaining more attention [3]

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:56.954340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06bf35fe-10ce-492b-8187-cccd90efe84b · outbound

This paper cites ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:57.108795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4053b3c0-093a-419b-8889-4b7bb6abfe36 · outbound

This paper cites an unresolved cited work.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Unresolved cited work

Reference 3

Resolution: malformed identifier; no resolver link, observed 2026-08-03T12:00:57.410466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e9ff464-e32d-40c1-abca-52cac495f2b8 · outbound

This paper cites an unresolved cited work.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:57.292347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b1ee6d2-3d86-4470-8032-10b3e767f42c · outbound

This paper cites Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:58.068320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af1d5073-10d3-43ff-aa6d-8d1ccf796b6d · outbound

This paper cites • In our experiments, FastWhisper achieved lower infer- ence latency than the original Whisper model while ensuring robust ASR performance across evaluation datasets.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition • In our experiments, FastWhisper achieved lower infer- ence latency than the original Whisper model while ensuring robust ASR performance across evaluation datasets

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:57.214287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 871f0c08-5ac4-4a6d-8f7c-b2c7b3e0e2b0 · outbound

This paper cites The use of ASKD and the Whisper encoder for training resulted in a 0.97% lower WER score compared to the teacher model, Whisper, despite the smaller dataset and fewer parameters.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition The use of ASKD and the Whisper encoder for training resulted in a 0.97% lower WER score compared to the teacher model, Whisper, despite the smaller dataset and fewer parameters

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:57.478674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51a66e0e-b52b-4a4d-b46a-e874da00ab54 · outbound

This paper cites Quantifying Bias in Automatic Speech Recognition.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Quantifying Bias in Automatic Speech Recognition

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:57.572649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2cf057d-2b0e-46d7-9970-beb852ed85e6 · outbound

This paper cites Far-ﬁeld au- tomatic speech recognition,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Far-ﬁeld au- tomatic speech recognition,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:57.595304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 950376e9-ed2e-4d29-aa43-94983fb58b53 · outbound

This paper cites Almost unsupervised text to speech and automatic spee ch recognition,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Almost unsupervised text to speech and automatic spee ch recognition,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:57.698813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc977ebe-56bd-4240-a86f-64c23cae287b · outbound

This paper cites wav2vec 2.0: A framework for self-supervised learni ng of speech representations,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition wav2vec 2.0: A framework for self-supervised learni ng of speech representations,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:57.896775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10fea597-1014-44f4-b2f1-3c105dac4fb0 · outbound

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

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Robust speech recognit ion via large-scale weak supervision,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:58.235876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f8b9de0-01d2-4dca-ad2f-40700603175a · outbound

This paper cites Beyond neural scaling laws: beating power l aw scaling via data pruning,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Beyond neural scaling laws: beating power l aw scaling via data pruning,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:58.366810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ea56402-9a5a-4bc9-afed-4fad49c86fc8 · outbound

This paper cites A better and faster end-to-end mo del for streaming asr,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition A better and faster end-to-end mo del for streaming asr,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:58.478492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51794e45-7b4c-4bcc-b1e7-5d53f102cbec · outbound

This paper cites ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:58.644990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 966d4251-6042-48b4-8ff5-bb0441201026 · outbound

This paper cites Iterative Compression of End-to-End ASR Model using AutoML.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Iterative Compression of End-to-End ASR Model using AutoML

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:58.773028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e9eed2-4164-4688-94cc-b0d95806c02c · outbound

This paper cites Multi-stage progressive compression o f con- former transducer for on-device speech recognition.,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Multi-stage progressive compression o f con- former transducer for on-device speech recognition.,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:58.870450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ffd4e67-5689-4d37-ac33-149271757589 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Distilling the Knowledge in a Neural Network

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:58.991437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d24a199-c8fb-423f-bd53-4e2cf8d05b4a · outbound

This paper cites Knowledge distillation: A survey,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Knowledge distillation: A survey,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:59.111579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a36d44dc-3fa4-4602-80cf-b50ac136407c · outbound

This paper cites Distil hubert: Speech representation learning by layer-wise distillatio n of hidden- unit bert,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Distil hubert: Speech representation learning by layer-wise distillatio n of hidden- unit bert,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:59.255489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5b8dcf7-51c6-401a-af52-af0466e4b2be · outbound

This paper cites Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:59.413512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d229d629-353b-42a9-9534-3b6858c8877e · outbound

This paper cites On informatio n and sufﬁciency,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition On informatio n and sufﬁciency,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:59.550083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb91cdc-7a55-46ae-b9da-29129d4833e3 · outbound

This paper cites FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:59.685825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9bc363-4f75-4f92-a9b2-9afd2b808b53 · outbound

This paper cites Masked token similarity transfer for compressing transfo rmer- based asr models,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Masked token similarity transfer for compressing transfo rmer- based asr models,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:59.851187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 708bac43-09ce-4dd7-ba98-6f8c88682d66 · outbound

This paper cites Does knowledge distillation re ally work?,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Does knowledge distillation re ally work?,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T12:00:59.963646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 147ef1ea-f90e-4e0b-9c7b-d4f5c829d982 · outbound

This paper cites EA-KD: Entropy-based Adaptive Knowledge Distillation.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition EA-KD: Entropy-based Adaptive Knowledge Distillation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:00.084468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 808a03a4-c75a-459a-a38c-b98a2aed7b5a · outbound

This paper cites AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:00.179828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fea69e3-ff2c-48d7-8f5a-7cc83ee5a6c7 · outbound

This paper cites Self-knowledge distillation with progressive reﬁ nement of targets,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Self-knowledge distillation with progressive reﬁ nement of targets,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:00.256764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b39c9108-1cc3-4e77-a9fb-df2a3a8e4c83 · outbound

This paper cites A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networks.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:00.357052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6a9947c-2c07-4214-931a-7c67c0d4b0f3 · outbound

This paper cites Librispeech: an asr corpus based on public domain a udio books,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Librispeech: an asr corpus based on public domain a udio books,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:00.451037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71ccd06c-13aa-493a-9deb-048099fd620b · outbound

This paper cites Ted-lium 3: Twice as much data and corpus repartition for experiments on speaker adap tation,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Ted-lium 3: Twice as much data and corpus repartition for experiments on speaker adap tation,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:00.519384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b377352d-ddd0-45ee-970a-ace2feecae05 · outbound

This paper cites The lj speech dataset,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition The lj speech dataset,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:00.617701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2ab651f-c346-4439-a1a5-af915a21c347 · outbound

This paper cites Earnings-22: A Practical Benchmark for Accents in the Wild.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Earnings-22: A Practical Benchmark for Accents in the Wild

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:00.692815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c07adfc1-48c4-4fc8-b406-c386f1f1b3e6 · outbound

This paper cites Unleashing the killer corpus: experie nces in creating the multi-everything ami meeting corpus,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Unleashing the killer corpus: experie nces in creating the multi-everything ami meeting corpus,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:00.865611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67ef9509-bed9-4fba-a2c6-3335ddaeeb53 · outbound

This paper cites GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:01.032776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65182b4b-4978-45c5-8537-f720ff8a725c · outbound

This paper cites V oxpopuli: A large-scale multilingual spe ech corpus for representation learning, semi-supervised learning and in- terpretation,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition V oxpopuli: A large-scale multilingual spe ech corpus for representation learning, semi-supervised learning and in- terpretation,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:01.148341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce3cfbe7-0fe9-4c5b-93c8-9beac092a11f · outbound

This paper cites GLU Variants Improve Transformer.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition GLU Variants Improve Transformer

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:01.242044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bbdd8a1-6e78-492f-8b5a-fc5aee908dc4 · outbound

This paper cites Nvidia nemo canary model pushes the frontier of speech recognition and translation,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Nvidia nemo canary model pushes the frontier of speech recognition and translation,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:01.315029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4416bbdf-bc15-4697-a8de-ba3f1ed5df83 · outbound

This paper cites C risper- whisper: Accurate timestamps on verbatim speech transcrip tions,.

ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition C risper- whisper: Accurate timestamps on verbatim speech transcrip tions,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T12:01:01.414371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 06bf35fe-10ce-492b-8187-cccd90efe84b · inbound