Paper Citation Record · LEDGER

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models

As of 22 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2505.16991.

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

pith.paper-citation-record.v1
2505.16991 v2

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:56:09.139143Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:56:06.320265Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T14:56:09.326991Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy26
unresolved4
parse uncertain0
malformed identifier2
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation becd972f-c10c-4ce3-acf5-626035daad5b · outbound

This paper cites Several efforts have been directed to create user and device-personalized models with adaptable model sizes while minimizing the latency using different tech- niques.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Several efforts have been directed to create user and device-personalized models with adaptable model sizes while minimizing the latency using different tech- niques

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:16.493633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a4c72ba3-40cc-4009-b31e-f6006ae35ce8 · outbound

This paper cites An Effective Training Framework for Light-Weight Automatic Speech Recognition Models.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models An Effective Training Framework for Light-Weight Automatic Speech Recognition Models

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T14:56:09.435784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 588f2426-8a7e-4a68-a927-a1cefcf4c5da · outbound

This paper cites an unresolved cited work.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Unresolved cited work

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:56:16.258713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 46abc907-3433-49ba-9c8b-696afd8cb9d2 · outbound

This paper cites an unresolved cited work.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Unresolved cited work

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:56:15.956298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 91aedfd0-a353-4465-b304-e585c0ae8e86 · outbound

This paper cites We demon- strated that a reference model can be employed to train a general light-weight encoder-only model that serves as a starting point for multiple light-weight networks.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models We demon- strated that a reference model can be employed to train a general light-weight encoder-only model that serves as a starting point for multiple light-weight networks

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:15.577334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2bead725-4fcc-48c3-a418-e52ee3c2f6aa · outbound

This paper cites Towards a person- alized clustered federated learning: A speech recognition case study,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Towards a person- alized clustered federated learning: A speech recognition case study,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:15.275108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 41471538-9722-48bd-b731-a7062fa127dd · outbound

This paper cites W H2D2N 2: Distributed ai-enabled ok-asn ser- vice for web of things,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models W H2D2N 2: Distributed ai-enabled ok-asn ser- vice for web of things,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:15.100430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a865f602-2956-4414-b51d-62e233be56e7 · outbound

This paper cites Learned token pruning for transformers,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Learned token pruning for transformers,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:14.840824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ab94d42a-a975-41b1-973d-d86baecd85c7 · outbound

This paper cites Model compression by iterative pruning with knowledge distillation and its application to speech enhancement.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Model compression by iterative pruning with knowledge distillation and its application to speech enhancement

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:14.524029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9077db30-5bdc-4cd5-94c9-2cbe5afde5bd · outbound

This paper cites Quantization aware training with absolute-cosine regularization for automatic speech recognition,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Quantization aware training with absolute-cosine regularization for automatic speech recognition,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:14.323149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4291995d-7a60-491f-808d-94141c7710e0 · outbound

This paper cites Lightweight and efficient end-to-end speech recognition using low-rank trans- former,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Lightweight and efficient end-to-end speech recognition using low-rank trans- former,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:14.033124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3acea7ac-9c1f-419f-905e-7a1827df3b23 · outbound

This paper cites Bottleneck low-rank transformers for low-resource spoken language understanding,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Bottleneck low-rank transformers for low-resource spoken language understanding,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:13.744248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 565a79af-bb46-409c-b9a3-3424d2899150 · outbound

This paper cites Student- teacher network learning with enhanced features,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Student- teacher network learning with enhanced features,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:13.461244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation df5e65bc-8253-4a15-9a39-4eebc9db7e69 · outbound

This paper cites Efficient knowledge distillation from an ensemble of teachers.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Efficient knowledge distillation from an ensemble of teachers

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:13.162473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 34045991-64f8-4d0d-b5d8-fb0e56913818 · outbound

This paper cites Investigation of sequence-level knowledge distillation methods for ctc acoustic models,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Investigation of sequence-level knowledge distillation methods for ctc acoustic models,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:12.871342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0b1c2633-49cf-4968-a416-884859b71f50 · outbound

This paper cites Knowledge distillation from offline to streaming rnn transducer for end-to-end speech recognition.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Knowledge distillation from offline to streaming rnn transducer for end-to-end speech recognition

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:12.623820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cd74b51c-d49e-4ec6-a06e-b9d7c7618f1e · outbound

This paper cites Tutornet: Towards flexible knowledge distillation for end-to-end speech recognition,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Tutornet: Towards flexible knowledge distillation for end-to-end speech recognition,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:12.397946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 35d881b5-2f15-4415-983b-b432cc54471d · outbound

This paper cites Knowledge distillation via module re- placing for automatic speech recognition with recurrent neural network transducer,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Knowledge distillation via module re- placing for automatic speech recognition with recurrent neural network transducer,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:12.165394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation baad5a5c-f6d1-4e74-8e1f-f6c9fc059ca6 · outbound

This paper cites Cons-kd: Dropout-robust knowledge distillation for ctc-based automatic speech recognition,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Cons-kd: Dropout-robust knowledge distillation for ctc-based automatic speech recognition,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:11.901129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 85f826db-de47-4273-9f69-94336b8d6501 · outbound

This paper cites Sparsification via compressed sensing for automatic speech recognition,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Sparsification via compressed sensing for automatic speech recognition,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:11.563828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e7fa9a57-c8ef-4ab5-ab96-b37719985668 · outbound

This paper cites Dynamic data pruning for automatic speech recognition,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Dynamic data pruning for automatic speech recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:11.273557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9cd95ea9-bf88-49dc-8fab-8b104d3d0a18 · outbound

This paper cites Training dynamic models using early exits for automatic speech recognition on resource-constrained devices.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Training dynamic models using early exits for automatic speech recognition on resource-constrained devices

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:07.925702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68f22dc9-9e8c-4e98-84b6-1dc6d7fe45ba · outbound

This paper cites LDASR: An experi- mental study on layer drop using conformer-based architecture,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models LDASR: An experi- mental study on layer drop using conformer-based architecture,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:11.065026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2eb45c1c-2a34-4f4a-8659-07a673d60f61 · outbound

This paper cites Fine-tuning strategies for faster inference using speech self-supervised models: a comparative study,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Fine-tuning strategies for faster inference using speech self-supervised models: a comparative study,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:10.912560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 27064111-8296-40dc-b0cd-1d2893a62216 · outbound

This paper cites Masked autoencoders are scalable vision learners,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Masked autoencoders are scalable vision learners,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:10.724630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 08319fbb-f1d8-4ef3-b365-620b90385792 · outbound

This paper cites Rethinking transformers pre-training for multi- spectral satellite imagery,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Rethinking transformers pre-training for multi- spectral satellite imagery,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:10.516006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 31a64396-f494-416c-9753-76d5da3b60eb · outbound

This paper cites Distilling the Knowledge in a Neural Network.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Distilling the Knowledge in a Neural Network

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:08.366164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d86f999c-d8fb-4367-88c7-d359fc071c05 · outbound

This paper cites Lessons from build- ing acoustic models with a million hours of speech,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Lessons from build- ing acoustic models with a million hours of speech,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:10.357423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d7cd1a3d-553a-43af-b53e-d3bd5113f7c4 · outbound

This paper cites Comparing kullback-leibler divergence and mean squared error loss in knowledge distillation,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Comparing kullback-leibler divergence and mean squared error loss in knowledge distillation,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:08.623944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 607c16d4-c0d3-4455-be09-cbca99171298 · outbound

This paper cites SentencePiece: A simple and lan- guage independent subword tokenizer and detokenizer for neural text processing,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models SentencePiece: A simple and lan- guage independent subword tokenizer and detokenizer for neural text processing,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:10.129839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 45d28b19-9124-4b2f-b737-202686025a65 · outbound

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

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Specaugment: A simple data augmentation method for automatic speech recognition,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:08.897488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1fd0297-873d-41b9-8675-6bb7a81e7dcb · outbound

This paper cites Librispeech: an asr corpus based on public do- main audio books,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Librispeech: an asr corpus based on public do- main audio books,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:09.889418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 82362cbb-e839-4a10-a679-a7276c4ef6c4 · outbound

This paper cites TED-LIUM 3: Twice as much data and corpus repartition for experiments on speaker adaptation,.

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models TED-LIUM 3: Twice as much data and corpus repartition for experiments on speaker adaptation,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:09.726646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Pith citing papers

Observation a4c72ba3-40cc-4009-b31e-f6006ae35ce8 · inbound