Pith. sign in

Paper Citation Record · LEDGER

Context-Driven Dynamic Pruning for Large Speech Foundation Models

As of 23 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 2 inbound Pith citation observations for arXiv:2505.18860.

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

pith.paper-citation-record.v1
2505.18860 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:29:14.171935Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:29:08.044481Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-28T17:12:25.097476Z

Reference resolution

42 of 42 outbound references displayed

  • verified exact0
  • verified fuzzy33
  • unresolved8
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7b330159-6399-4c9e-9fca-7a73f88e2c7f · outbound

This paper cites These speech foundation models demon- strate strong generalization ability and robustness across lan- guages [3], speakers, and acoustic conditions [1].

Context-Driven Dynamic Pruning for Large Speech Foundation Models These speech foundation models demon- strate strong generalization ability and robustness across lan- guages [3], speakers, and acoustic conditions [1]

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:24.918993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:07.916684Z digest=sha256:f71b8633c43060ce63f1da27558bbc005439e6b5d357444a49a60a3cf86e5c40

Observation f432fb50-9ff4-4e00-b822-9535741ff7ae · outbound

This paper cites Context-Driven Dynamic Pruning for Large Speech Foundation Models.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Context-Driven Dynamic Pruning for Large Speech Foundation Models

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:08.044481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:08.044481Z digest=sha256:fae8c6639c12c177123791e56ec3ca516f804e598e5bcaa072dcfb4b937ad15c

Observation 1017a677-2ca2-4d9e-8aff-3a6c82708e0f · outbound

This paper cites Local Gate Predictor In localGP, the pruning maskzis computed separately for each layer.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Local Gate Predictor In localGP, the pruning maskzis computed separately for each layer

Reference 3

Resolution
malformed identifier
raw_fallback, observed 2026-08-07T14:29:24.553447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:08.165498Z digest=sha256:09e1d0d56c6b37ab7a1f1594c4c3dbbeb36aa6e549361b397e36c63579edc29b

Observation db3c2d39-ef0d-4941-8937-509d27c5e207 · outbound

This paper cites an unresolved cited work.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Unresolved cited work

Reference 4

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:29:24.225442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:08.324003Z digest=sha256:c349136fc986e54a8bcda11a26230f68ce99297459c9d84e0a85a7032ed92367

Observation 593d94ee-ae03-4819-8a87-84fdeadbe2ad · outbound

This paper cites an unresolved cited work.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:29:23.557920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:08.682694Z digest=sha256:acf64a3f314c5f313daa7dfd01f139eacde5b7e840594888bb392db22d0749a2

Observation a53fe0bc-8679-44b7-8549-433b744c465a · outbound

This paper cites an unresolved cited work.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:08.820355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:08.820355Z digest=sha256:25b158221e522e06438e15db7335ee12ee1db28d437162f3a20f31b0f2fcdc57

Observation ec257d9b-3e62-467a-92f0-f9dfce5d2a1c · outbound

This paper cites Colld: Contrastive layer-to-layer distillation for compressing multilingual pre-trained speech encoders,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Colld: Contrastive layer-to-layer distillation for compressing multilingual pre-trained speech encoders,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:22.249161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:09.860129Z digest=sha256:3bf22c87acace7d6ac4f15883b9f71ee47fec443d0ef36d21ae034d04bb64efe

Observation 6e27afa5-9cf0-4c39-97b0-3cbd119c2240 · outbound

This paper cites an unresolved cited work.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Unresolved cited work

Reference 8

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:29:23.890200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:08.504355Z digest=sha256:1de1b31ef2309a0c4a3425634381ea55cb36fe67caac7a08cf938623919eab40

Observation abcc7e10-178a-4ba5-9615-f7168bf823e8 · outbound

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

Context-Driven Dynamic Pruning for Large Speech Foundation Models Robust speech recognition via large-scale weak supervision,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:08.962813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:08.962813Z digest=sha256:0d3eb0553532730de9202377220df9109b6406e5e43ecfca79a08b17d4536d64

Observation c8aefc18-9d3e-438a-8eb8-b55fc2f9360f · outbound

This paper cites Less is more: Accu- rate speech recognition & translation without web-scale data,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Less is more: Accu- rate speech recognition & translation without web-scale data,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:23.229891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:09.110260Z digest=sha256:1ceb4b0d734121be8d648b324550781db19e2c71de3da7686acb84a09c097d87

Observation 8cfc4100-3c36-4267-9218-487531fe4f54 · outbound

This paper cites Scaling Speech Technology to 1,000+ Languages.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Scaling Speech Technology to 1,000+ Languages

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:09.278802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:09.278802Z digest=sha256:6b787e6ce682fe0e9dd8b13d34ca13d11c9b4ae554d5638f3befcb6ba20482f1

Observation 8c2e6f08-56d5-4ed9-bf0d-5472dee330ef · outbound

This paper cites Owsm v3.1: Better and faster open whisper-style speech models based on e-branchformer,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Owsm v3.1: Better and faster open whisper-style speech models based on e-branchformer,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:22.948762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:09.440497Z digest=sha256:4fdc5385b28fd7baa0d85e687f8b72833af744d797fe2e5be9194110de45c731

Observation 947f67ed-b0ce-43b7-bf5d-60bc5a84be26 · outbound

This paper cites Distil-whisper: Robust knowledge distillation via large-scale pseudo labelling,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Distil-whisper: Robust knowledge distillation via large-scale pseudo labelling,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:22.691275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:09.561275Z digest=sha256:4e3afdd7d3aef00d79bfa2612b5961d897c7b7e80c05907da9e96a66ae62c548

Observation 0b46909b-cb61-4903-9695-888ae3a8762e · outbound

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

Context-Driven Dynamic Pruning for Large Speech Foundation Models Distilhubert: Speech representation learning by layer-wise distillation of hidden-unit bert,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:22.376137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:09.685508Z digest=sha256:75c6c2748ed2a16c2c76de196023be03fa8f4ab05a3099b00e0695dce0b56b38

Observation 47b61b29-6d5f-4dac-80f5-2334f8006ab4 · outbound

This paper cites 4-bit quantization of lstm- based speech recognition models,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models 4-bit quantization of lstm- based speech recognition models,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:22.098308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:10.029344Z digest=sha256:ed6cc0c82b69d754dbe32dc3a216204bf97fa974ce9ac28167b7549066bb73b4

Observation 07440e7e-6c8d-4ca5-9f4c-86a02e0a6619 · outbound

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

Context-Driven Dynamic Pruning for Large Speech Foundation Models 2-bit conformer quantization for automatic speech recog- nition,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:21.876154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:10.173876Z digest=sha256:8478dd5c00105e96e23ee346c01b42199125e37496fd1d580e4d6ec57de65263

Observation 76dfb02b-3a95-4d89-8df4-8838869252db · outbound

This paper cites Usm-lite: Quan- tization and sparsity aware fine-tuning for speech recognition with universal speech models,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Usm-lite: Quan- tization and sparsity aware fine-tuning for speech recognition with universal speech models,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:21.684343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:10.285353Z digest=sha256:c33cd01a540e4106d247c9b6c688fdec6404412b91bd9330cd20f6347e888658

Observation cce01abf-c812-4bf9-868c-b03b518e456c · outbound

This paper cites Learning N: M fine-grained struc- tured sparse neural networks from scratch,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Learning N: M fine-grained struc- tured sparse neural networks from scratch,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:21.455273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:10.397113Z digest=sha256:0ee4aa06561ee22c78a844842962c2343af168cf8659fde224d8a8720a4e9d58

Observation 8ce8656a-147f-4bbc-8b95-6ebca5ddb383 · outbound

This paper cites Learning sparse neu- ral networks throughl 0 regularization,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Learning sparse neu- ral networks throughl 0 regularization,

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:21.246779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:10.515004Z digest=sha256:c7cd964cb7b5ed5f9b6e700fd345f3f73ba9f3c4c559675c0ca19fd838f53ae1

Observation 60a55caa-6c93-4af9-8017-50572f3b4afc · outbound

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

Context-Driven Dynamic Pruning for Large Speech Foundation Models Parp: Prune, adjust and re-prune for self-supervised speech recognition,

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:21.039024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:10.633905Z digest=sha256:8ef4aca63cb3688c92279d9cd615602bc343e6fc3e8b23113c07297a59157bb0

Observation fb056d90-36be-4362-bb12-716633aa052e · outbound

This paper cites Structured pruning of self-supervised pre-trained models for speech recog- nition and understanding,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Structured pruning of self-supervised pre-trained models for speech recog- nition and understanding,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:20.777318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:10.791637Z digest=sha256:b25b796675bca4b12581cd6c09af01979a58ca314673899a58c0990cfceacb8f

Observation 27d201b7-0da7-42cf-856b-a2b6dbffc428 · outbound

This paper cites Context-aware dynamic pruning for speech foundation models,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Context-aware dynamic pruning for speech foundation models,

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:20.471808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:10.934814Z digest=sha256:add22ca690226741e09795ebb7b47e9aec0edb1c51984511be644e21aa1be860

Observation df93b72c-fd0e-464f-85fb-e18b5b534fc4 · outbound

This paper cites Dphubert: Joint distillation and pruning of self-supervised speech models,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Dphubert: Joint distillation and pruning of self-supervised speech models,

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:20.160846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:11.115509Z digest=sha256:a99f400f8ce708c243de5a5fe1e4e69a6a973a5e022d5621be4f182322bd9231

Observation c9c5d0b1-8907-4e47-8d91-f1416af765a5 · outbound

This paper cites Dynamic to- ken pruning in plain vision transformers for semantic segmenta- tion,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Dynamic to- ken pruning in plain vision transformers for semantic segmenta- tion,

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:19.874510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:11.335602Z digest=sha256:3c9ce551849fe675844f5c26c8b0ae907da18bb18f6f0c1f585c5c576fe360e1

Observation 3c3be4cc-d8dd-49ea-bf55-00f3587a3845 · outbound

This paper cites Trainable dynamic subsampling for end-to-end speech recognition,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Trainable dynamic subsampling for end-to-end speech recognition,

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:19.582075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:11.520782Z digest=sha256:10296dac4b274f0a630831499ce40e6cc0baa14d5b4cd20bb12a8f136778ff5c

Observation c2408415-ecd6-4a59-8198-bc6bb42814da · outbound

This paper cites Adaptive Computation Time for Recurrent Neural Networks.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Adaptive Computation Time for Recurrent Neural Networks

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:11.652369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:11.652369Z digest=sha256:fc82f00c5e8faa9cd4bfdd30dd94f5570765185a45c3b65eb52641309296da55

Observation d8036dd9-3391-4dbf-95cd-52f212778d39 · outbound

This paper cites Avoid overthinking in self-supervised models for speech recognition,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Avoid overthinking in self-supervised models for speech recognition,

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:19.208376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:11.821394Z digest=sha256:5b5e03f839d405d934a48ca34a93af7590b32396653025b8199695dddc6b044f

Observation bc69b650-a27a-4ba4-a1d2-79b67cdcc535 · outbound

This paper cites Efficient sequence transduction by jointly predicting tokens and durations,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Efficient sequence transduction by jointly predicting tokens and durations,

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:18.920535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:11.957968Z digest=sha256:8fa90df407859c621bd703e209bbaa76026bada62f4026626d3de56ee3df4acd

Observation 807d090c-9764-43a7-9bf3-dd428ab3674f · outbound

This paper cites I3d: Transformer architectures with input-dependent dynamic depth for speech recognition,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models I3d: Transformer architectures with input-dependent dynamic depth for speech recognition,

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:18.600487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:12.085678Z digest=sha256:3bc4c345cb03fd849904e5aba943d984b6748897a7433b109766368f3fa8e533

Observation 41d26a1a-a7e0-40be-abe7-5adc63ced150 · outbound

This paper cites Ecapa-tdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Ecapa-tdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification,

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:18.310215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:12.212950Z digest=sha256:6e9de22f3516d883d46b4a824d8b40013b42067c1bf1c1e292862fc903459fa6

Observation de839497-785b-48a0-b39d-867effb51078 · outbound

This paper cites Beats: audio pre-training with acoustic tok- enizers,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Beats: audio pre-training with acoustic tok- enizers,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:17.974233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:12.414497Z digest=sha256:395b7b12661ca4d83cbff4f931f3e0033a16cff191a220f68c52520560c5cf70

Observation ece424b7-361d-4f13-82f8-836a5c354096 · outbound

This paper cites Uriel and lang2vec: Representing languages as typo- logical, geographical, and phylogenetic vectors,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Uriel and lang2vec: Representing languages as typo- logical, geographical, and phylogenetic vectors,

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:17.662502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:12.601790Z digest=sha256:97d02a66e74ebc3381dcbae56195eb097e50577823f228d5cf87bb46d16d5dd6

Observation 62907125-08bd-44f3-8e60-ee00e0e7b91b · outbound

This paper cites Re- thinking pruning for accelerating deep inference at the edge,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Re- thinking pruning for accelerating deep inference at the edge,

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:17.344486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:12.827792Z digest=sha256:8b1c6961680b8c4ed5671bd2506ddbf8ec3e26c6fcfde20978e981f4213c12a5

Observation dce3d83e-e8c3-4da3-834e-89887170107b · outbound

This paper cites Audio lottery: Speech recog- nition made ultra-lightweight, noise-robust, and transferable,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Audio lottery: Speech recog- nition made ultra-lightweight, noise-robust, and transferable,

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:17.042974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:13.005300Z digest=sha256:6d5dfdbf71fa09276b4745c0bcb530d8a9c96f95dd4becb6ce7784350c06f792

Observation 25c4276f-ee1c-4af4-947e-61d5aff56b71 · outbound

This paper cites Compute cost amortized transformer for streaming asr,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Compute cost amortized transformer for streaming asr,

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:16.717469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:13.188516Z digest=sha256:d9a2d4c3046c2b1746437bc0d2feb5972c76362b985d28e8d1512c486d48d339

Observation debfcfc5-2afc-4cd3-b2b2-77768e05cc4c · outbound

This paper cites Amortized neural networks for low-latency speech recognition,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Amortized neural networks for low-latency speech recognition,

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:16.505429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:13.336662Z digest=sha256:82f20bfacaa7d1f8392acf46749ed0ffdc4bc3a4df75032eb5336c9d7598b413

Observation 8912c93c-6e55-4e94-829d-ba5b2c26c06a · outbound

This paper cites A study of the recur- rent neural network encoder-decoder for large vocabulary speech recognition,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models A study of the recur- rent neural network encoder-decoder for large vocabulary speech recognition,

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:16.219668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:13.481442Z digest=sha256:3472abdfadc019ce60ba36b2e75a01be0e4e09939cb42685152047b6eb7ad8a6

Observation aa95ee3b-d6b3-4250-916f-a0f81bdb3000 · outbound

This paper cites Adaptive feature selection for end-to-end speech translation,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Adaptive feature selection for end-to-end speech translation,

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:15.935341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:13.618980Z digest=sha256:0e965352e7f94001aa64bfce0abc8786c78f452ef9d12af652e52f8e846258a5

Observation 77a5d6af-230b-48ed-8f07-88e386bfe0ce · outbound

This paper cites Categorical reparameterization with gumbel-softmax,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Categorical reparameterization with gumbel-softmax,

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:15.601396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:13.787442Z digest=sha256:ee17a4b20dce39bfb83da8d1c1c549fd44a30e14458d08fa23ef0e0ae6e06cdd

Observation a144d106-d681-4dfc-8988-804fb9f7bb48 · outbound

This paper cites MLP-based architecture with variable length input for automatic speech recognition,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models MLP-based architecture with variable length input for automatic speech recognition,

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:15.178206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:13.915098Z digest=sha256:83a7823faeb0e0d68a239e2db664225b8a2cb9195022ffcb728d07903f0c489b

Observation 22592b5e-1e2e-4f5e-9a14-bc14b57e2c82 · outbound

This paper cites E-branchformer: Branchformer with enhanced merging for speech recognition,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models E-branchformer: Branchformer with enhanced merging for speech recognition,

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:14.864273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:14.044902Z digest=sha256:1979d93f48e20e3272b68b90c1dd4b7b204d12130df0b3fe632d4e4a4de3a615

Observation f81c8cda-f7ad-43f0-92cf-34f9fb0745a9 · outbound

This paper cites Europarl-st: A multilingual corpus for speech translation of parliamentary de- bates,.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Europarl-st: A multilingual corpus for speech translation of parliamentary de- bates,

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:29:14.531207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-08-07T14:29:14.171935Z digest=sha256:fbc1081ef118c47959af88a46b003c77761b60790254689ab4fb46e84b0fcb5a

Pith citing papers

Observation f432fb50-9ff4-4e00-b822-9535741ff7ae · inbound

Context-Driven Dynamic Pruning for Large Speech Foundation Models cites this paper.

Context-Driven Dynamic Pruning for Large Speech Foundation Models Context-Driven Dynamic Pruning for Large Speech Foundation Models

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T14:29:08.044481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:29:08.044481Z digest=sha256:fae8c6639c12c177123791e56ec3ca516f804e598e5bcaa072dcfb4b937ad15c

Observation baff783a-0c4c-41f5-ab30-3877d2cfc228 · inbound

MURMUR: An Efficient Inference System for Long-Form ASR cites this paper.

MURMUR: An Efficient Inference System for Long-Form ASR Context-Driven Dynamic Pruning for Large Speech Foundation Models

Reference 31

Resolution
verified exact
arxiv_id, observed 2026-06-28T17:12:25.099036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=arxiv_source observed=2026-06-28T17:06:02.978205Z digest=sha256:3ac66bcf8bd1de4b46e0b9590a9927f8f12fc8b7f52e2a8f9a9a19ec389bb4a4