Paper Citation Record · LEDGER

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates

As of 22 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 1 inbound Pith citation observation for arXiv:2505.22608.

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

pith.paper-citation-record.v1
2505.22608 v1

Coverage vector

measured 53 of 53 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:07:47.252902Z

measured 54 of 54 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 2026-08-07T13:07:42.436192Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T13:07:47.409372Z

Reference resolution

53 of 53 outbound references displayed

verified exact1
verified fuzzy43
unresolved8
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 220e7b34-9490-466d-a854-a3c6cf564dc4 · outbound

This paper cites structured.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates structured

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:56.274196Z

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 4c8ef2a8-301f-46f6-bd1e-938fe3666ffc · outbound

This paper cites Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:07:47.487116Z

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 90052f7e-1e21-49b5-9d6e-f9392bc11563 · outbound

This paper cites In contrast, previous fine-grained ap- proach [21] performed pruning and fine-tuning separately.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates In contrast, previous fine-grained ap- proach [21] performed pruning and fine-tuning separately

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:56.090123Z

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 2bc9efce-cb7d-481a-ad6b-6074cb017404 · outbound

This paper cites an unresolved cited work.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:07:55.908943Z

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 5a53e0d1-0890-45b3-85d6-5f866af29204 · outbound

This paper cites an unresolved cited work.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:07:55.706648Z

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 ec4b7207-93c5-4afb-9bf6-bfa4d91ad4ae · outbound

This paper cites For example, HuBERT consists of a CNN encoder, a Transformer encoder, a projection layer and a code embedding layer.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates For example, HuBERT consists of a CNN encoder, a Transformer encoder, a projection layer and a code embedding layer

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:55.525413Z

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 8f8b737c-8665-4b01-b829-5cf37f99aa62 · outbound

This paper cites an unresolved cited work.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:07:55.379435Z

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 2b85ed7d-6511-4bed-b615-7e30310c8769 · outbound

This paper cites an unresolved cited work.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:07:55.242426Z

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 131230ee-6705-4625-8500-92cb4b93422a · outbound

This paper cites The training loss is given by: L = Lctc + η X l ∥M l ∥0, (7) where η is a constant coefficient to control the overall sparsity.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates The training loss is given by: L = Lctc + η X l ∥M l ∥0, (7) where η is a constant coefficient to control the overall sparsity

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:55.074890Z

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 9a6798f2-3a40-4725-9f41-2cfb2a34a5c5 · outbound

This paper cites (” and “).

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates (” and “)

Reference 10

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:07:54.886768Z

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 8b2da167-59c3-409b-857f-357ad7487955 · outbound

This paper cites Our method shows superior performance under the same model-size constraint while reduc- ing the fine-tuning time compared to the previous works.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Our method shows superior performance under the same model-size constraint while reduc- ing the fine-tuning time compared to the previous works

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:54.688022Z

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 ae931572-fc99-48b4-80b8-30cdeafaf3bb · outbound

This paper cites 14200220, 14200021, 14200324 and Innovation Technology Fund grant No.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates 14200220, 14200021, 14200324 and Innovation Technology Fund grant No

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:07:43.265151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c1fc36b-380d-4055-8f52-ccaab9f4e9ee · outbound

This paper cites wav2vec 2.0: A frame- work for self-supervised learning of speech representations,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates wav2vec 2.0: A frame- work for self-supervised learning of speech representations,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:54.489177Z

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 2d9f54bd-1719-420a-bbb9-edfb806218f7 · outbound

This paper cites HuBERT: Self- supervised speech representation learning by masked prediction of hidden units,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates HuBERT: Self- supervised speech representation learning by masked prediction of hidden units,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:54.246773Z

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 4a302ebd-f273-4078-abb1-f65c915dc3f1 · outbound

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

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates WavLM: Large-scale self- supervised pre-training for full stack speech processing,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:54.089478Z

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 68474099-6091-4039-a308-028f7dc83bb5 · outbound

This paper cites 2-bit conformer quantization for automatic speech recognition,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates 2-bit conformer quantization for automatic speech recognition,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:53.872627Z

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 2d6b3d29-dc99-4693-9e9b-525a6212fe22 · outbound

This paper cites 4-bit conformer with na- tive quantization aware training for speech recognition,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates 4-bit conformer with na- tive quantization aware training for speech recognition,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:53.659506Z

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 19e7bd96-22ab-4617-b639-8da638ab1515 · outbound

This paper cites I-bert: Integer-only bert quantization,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates I-bert: Integer-only bert quantization,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:53.395361Z

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 fd737b77-4776-45d5-aadc-8b32298875a9 · outbound

This paper cites Effective and Efficient Mixed Precision Quantization of Speech Foundation Models.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Effective and Efficient Mixed Precision Quantization of Speech Foundation Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:07:43.930104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d395416c-e69f-4ac1-9220-faa053cf7776 · outbound

This paper cites A model for every user and budget: Label-free and personalized mixed-precision quantiza- tion,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates A model for every user and budget: Label-free and personalized mixed-precision quantiza- tion,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:53.179626Z

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 b7c3f0c7-f0ac-4848-9a48-bcdb6d8c54b7 · outbound

This paper cites Efficient conformer-based speech recognition with linear attention,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Efficient conformer-based speech recognition with linear attention,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:52.875857Z

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 7c629c2d-ea39-4781-8adf-c5d21003e429 · outbound

This paper cites Lossless 4-bit quantization of architecture compressed conformer asr systems on the 300-hr switchboard corpus,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Lossless 4-bit quantization of architecture compressed conformer asr systems on the 300-hr switchboard corpus,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:52.735004Z

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 3635c027-2878-45df-89d9-17e54d45f331 · outbound

This paper cites Unstructured pruning and low rank factorisation of self-supervised pre-trained speech models,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Unstructured pruning and low rank factorisation of self-supervised pre-trained speech models,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:52.619325Z

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 4495ae43-81f9-435f-8fac-5fceb99060a2 · outbound

This paper cites Multi-stage progres- sive compression of conformer transducer for on-device speech recognition,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Multi-stage progres- sive compression of conformer transducer for on-device speech recognition,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:52.418180Z

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 3f9c0ab4-a4df-44ac-8f78-d885327405fd · outbound

This paper cites Conformer-based on-device stream- ing speech recognition with KD compression and two-pass archi- tecture,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Conformer-based on-device stream- ing speech recognition with KD compression and two-pass archi- tecture,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:52.206246Z

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 57f51ee2-a27d-4168-af7c-c55781caa3f9 · outbound

This paper cites DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:07:44.557979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4a906b9-d675-4fd8-b654-f02d4d5e66d9 · outbound

This paper cites DistilHuBERT: Speech representation learning by layer-wise distillation of hidden-unit bert,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates DistilHuBERT: Speech representation learning by layer-wise distillation of hidden-unit bert,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:52.016317Z

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 a8e23fd6-3d1e-40d5-9ccd-8a8fbd029f67 · outbound

This paper cites LightHuBERT: Lightweight and configurable speech representation learning with once-for-all hidden-unit bert,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates LightHuBERT: Lightweight and configurable speech representation learning with once-for-all hidden-unit bert,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:51.813622Z

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 07983b3b-b1c8-4ff5-984e-74f2022f849d · outbound

This paper cites Deep versus wide: An analysis of student architectures for task-agnostic knowledge dis- tillation of self-supervised speech models,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Deep versus wide: An analysis of student architectures for task-agnostic knowledge dis- tillation of self-supervised speech models,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:51.618942Z

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 a3896745-de06-4fa4-984f-8f1a2bb1eae6 · outbound

This paper cites FitHuBERT: Going thinner and deeper for knowledge distillation of speech self-supervised learn- ing,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates FitHuBERT: Going thinner and deeper for knowledge distillation of speech self-supervised learn- ing,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:51.388201Z

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 436b4a62-1f55-4b27-a73e-d7343e6e3487 · outbound

This paper cites Dynamic sparsity neural net- works for automatic speech recognition,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Dynamic sparsity neural net- works for automatic speech recognition,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:51.207154Z

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 fda58d33-294c-4e94-bb6e-9f6e1601861f · outbound

This paper cites Layer pruning on demand with intermediate ctc,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Layer pruning on demand with intermediate ctc,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:51.023211Z

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 44fa1aa1-a747-4645-8313-6c1086722d9c · outbound

This paper cites Sparsewav: Fast and accurate one- shot unstructured pruning for large speech foundation models,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Sparsewav: Fast and accurate one- shot unstructured pruning for large speech foundation models,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:50.779492Z

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 c12b43bb-7af1-4fdc-a9c4-337d3690e5f9 · outbound

This paper cites Task-agnostic structured pruning of speech representation models,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Task-agnostic structured pruning of speech representation models,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:50.644894Z

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 a5464502-6262-40f0-a7e8-081e62e28647 · outbound

This paper cites Accurate and structured prun- ing for efficient automatic speech recognition,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Accurate and structured prun- ing for efficient automatic speech recognition,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:50.505619Z

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 d80de02e-022e-4856-8874-ece3dc39f595 · outbound

This paper cites PADA: Pruning assisted domain adaptation for self-supervised speech representations,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates PADA: Pruning assisted domain adaptation for self-supervised speech representations,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:50.418610Z

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 726515f2-f2dc-467d-8113-6a40a72c321f · outbound

This paper cites Structured pruning of self- supervised pre-trained models for speech recognition and under- standing,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Structured pruning of self- supervised pre-trained models for speech recognition and under- standing,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:50.292961Z

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 5c3e081d-30d8-4611-b313-d3fb067f7fde · outbound

This paper cites One-pass multiple conformer and foundation speech systems compression and quantization using an all-in-one neural model,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates One-pass multiple conformer and foundation speech systems compression and quantization using an all-in-one neural model,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:50.194985Z

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 aabd67fa-7cf3-498e-be55-0c77628b1634 · outbound

This paper cites Deep compres- sion of pre-trained transformer models,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Deep compres- sion of pre-trained transformer models,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:50.024685Z

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 799ec405-81e1-4709-a4a8-b41222e58107 · outbound

This paper cites USM-Lite: Quantization and sparsity aware fine-tuning for speech recognition with universal speech models,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates USM-Lite: Quantization and sparsity aware fine-tuning for speech recognition with universal speech models,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:49.887440Z

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 ee849262-73fa-42e6-a42f-86fd34607ffa · outbound

This paper cites DPHuBERT: Joint dis- tillation and pruning of self-supervised speech models,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates DPHuBERT: Joint dis- tillation and pruning of self-supervised speech models,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:49.718337Z

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 ec6f616c-5af9-46e0-b51f-44ec33e4e860 · outbound

This paper cites Skill: Similarity- aware knowledge distillation for speech self-supervised learning,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Skill: Similarity- aware knowledge distillation for speech self-supervised learning,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:49.538003Z

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 1950e51b-e240-4c81-95fc-9342a96e1e8d · outbound

This paper cites Some statistical issues in the comparison of speech recognition algorithms,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Some statistical issues in the comparison of speech recognition algorithms,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:49.355489Z

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 73f309c5-6a13-4841-8b7a-f0eca1a23dab · outbound

This paper cites Parp: Prune, adjust and re- prune for self-supervised speech recognition,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Parp: Prune, adjust and re- prune for self-supervised speech recognition,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:49.210449Z

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 a3e4a70c-a3df-4c71-ae68-32ed0316a147 · outbound

This paper cites Learning asr pathways: A sparse multilingual asr model,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Learning asr pathways: A sparse multilingual asr model,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:49.075383Z

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 7614c5de-c66c-484f-8806-0ada0f472378 · outbound

This paper cites Learnable sparsity structured pruning for acoustic pre-trained models,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Learnable sparsity structured pruning for acoustic pre-trained models,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:48.942490Z

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 db2da0c5-c291-4292-a238-e1e121694e0f · outbound

This paper cites Losses can be blessings: Routing self-supervised speech representations towards efficient multilin- gual and multitask speech processing,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Losses can be blessings: Routing self-supervised speech representations towards efficient multilin- gual and multitask speech processing,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:48.798261Z

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 b6ae83e2-a4b6-4338-b44c-bb201a8b40e4 · outbound

This paper cites Darts: Differentiable archi- tecture search,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Darts: Differentiable archi- tecture search,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:48.683077Z

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 5279adb7-d191-46b9-9f5f-a7c7435b4b89 · outbound

This paper cites The concrete distri- bution: A continuous relaxation of discrete random variables,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates The concrete distri- bution: A continuous relaxation of discrete random variables,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:48.389237Z

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 100f789c-f437-4ce4-989e-f6295119c85b · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T13:07:46.881176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb341084-5a82-40b2-a925-89159b24f8bf · outbound

This paper cites LibriSpeech: an asr cor- pus based on public domain audio books,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates LibriSpeech: an asr cor- pus based on public domain audio books,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:48.172041Z

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 d21190ff-b2dd-42cd-863c-0ae87033d2d3 · outbound

This paper cites Superb: Speech pro- cessing universal performance benchmark,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Superb: Speech pro- cessing universal performance benchmark,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:47.898512Z

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 a5b21bcf-35e8-4e00-9456-8acc187a9b46 · outbound

This paper cites Distilling HuBERT with LSTMs via decoupled knowledge distillation,.

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates Distilling HuBERT with LSTMs via decoupled knowledge distillation,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:07:47.722547Z

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 4c8ef2a8-301f-46f6-bd1e-938fe3666ffc · inbound