Paper Citation Record · LEDGER

Input Conditioned Layer Dropping in Speech Foundation Models

As of 22 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 1 inbound Pith citation observation for arXiv:2507.07954.

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

pith.paper-citation-record.v1
2507.07954 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:32:10.105502Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:32:07.527161Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T18:32:10.455611Z

Reference resolution

46 of 46 outbound references displayed

verified exact2
verified fuzzy42
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation dc9d661c-e363-4bcf-91e1-1f69de1aab55 · outbound

This paper cites However, their practicality on low resources / edge devices is limited due to significant com- putational overhead and enormous memory requirement.

Input Conditioned Layer Dropping in Speech Foundation Models However, their practicality on low resources / edge devices is limited due to significant com- putational overhead and enormous memory requirement

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:17.970260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c122f81d-389a-43b4-8ef4-96971f9825e1 · outbound

This paper cites We will restrict the discus- sion to dynamic depth only as it encapsulates the early exit and layer dropping approaches.

Input Conditioned Layer Dropping in Speech Foundation Models We will restrict the discus- sion to dynamic depth only as it encapsulates the early exit and layer dropping approaches

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:17.856353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8d6f4988-da0b-4083-b92f-897039b76745 · outbound

This paper cites For each input sample, the LS block selects the finest combination of encoder layers achieving optimal performance for various resource settings.

Input Conditioned Layer Dropping in Speech Foundation Models For each input sample, the LS block selects the finest combination of encoder layers achieving optimal performance for various resource settings

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:17.749181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8962fbf7-73bc-43ef-83d4-5fb2078595d1 · outbound

This paper cites We utilized well- known transformer-based foundation models: (i) WavLM.

Input Conditioned Layer Dropping in Speech Foundation Models We utilized well- known transformer-based foundation models: (i) WavLM

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:17.651407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f90cb0f4-12fe-43c4-80e5-e1baf115bfda · outbound

This paper cites an unresolved cited work.

Input Conditioned Layer Dropping in Speech Foundation Models Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-06T18:32:17.463460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation be7a05f4-3e83-41b3-868d-7b7e5c104d6c · outbound

This paper cites Dynamic split computing for efficient deep edge intelligence,.

Input Conditioned Layer Dropping in Speech Foundation Models Dynamic split computing for efficient deep edge intelligence,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:16.585614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 76dec4ca-c6f0-4718-9f4f-b1e8b23b40dd · outbound

This paper cites Split computing and early exiting for deep learning applications: Survey and research chal- lenges,.

Input Conditioned Layer Dropping in Speech Foundation Models Split computing and early exiting for deep learning applications: Survey and research chal- lenges,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:16.408886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 21e6e435-9af1-4bff-91f8-7bb5571d3312 · outbound

This paper cites Learned token pruning for trans- formers,.

Input Conditioned Layer Dropping in Speech Foundation Models Learned token pruning for trans- formers,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:17.359194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 068438fe-3d1c-439c-af4e-80019f1c267a · outbound

This paper cites Input Conditioned Layer Dropping in Speech Foundation Models.

Input Conditioned Layer Dropping in Speech Foundation Models Input Conditioned Layer Dropping in Speech Foundation Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:32:10.539869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c6d8ee10-b44d-47c5-bd97-cd2f438b2345 · outbound

This paper cites FastFormers: Highly efficient transformer models for natural language understand- ing,.

Input Conditioned Layer Dropping in Speech Foundation Models FastFormers: Highly efficient transformer models for natural language understand- ing,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:17.207676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 197efa5e-265b-4aee-97da-04f2fa5b77d6 · outbound

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

Input Conditioned Layer Dropping in Speech Foundation Models Lightweight and efficient end-to-end speech recognition using low-rank trans- former,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:17.045500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 04c53678-c757-4ee2-8cf5-6d2433584b48 · outbound

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

Input Conditioned Layer Dropping in Speech Foundation Models Bottleneck low-rank transformers for low-resource spoken language understanding,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:16.896664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 68b18cd7-c2e2-445e-ad70-66e88cc6e953 · outbound

This paper cites Tensor decomposition for minimization of E2E SLU model toward on-device pro- cessing,.

Input Conditioned Layer Dropping in Speech Foundation Models Tensor decomposition for minimization of E2E SLU model toward on-device pro- cessing,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:16.731090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 27851904-01e3-4a46-aadf-a2e0add435ae · outbound

This paper cites Accelerating training of transformer-based language models with progressive layer dropping,.

Input Conditioned Layer Dropping in Speech Foundation Models Accelerating training of transformer-based language models with progressive layer dropping,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:15.466113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6e3e637b-a512-431d-b543-9cd6cc7d400d · outbound

This paper cites HuBERT-EE: Early exiting Hu- BERT for efficient speech recognition,.

Input Conditioned Layer Dropping in Speech Foundation Models HuBERT-EE: Early exiting Hu- BERT for efficient speech recognition,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:16.256411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2e6f887d-1fa2-4288-baf5-bf61b858da8e · outbound

This paper cites We employ Word Error Rate (WER) metric for ASR, and accuracy for the other tasks.

Input Conditioned Layer Dropping in Speech Foundation Models We employ Word Error Rate (WER) metric for ASR, and accuracy for the other tasks

Reference 16

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T18:32:17.602459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b9c9190a-4f63-4d46-8ddb-4300b1a8d5c8 · outbound

This paper cites Fine-tuning strategies for faster in- ference using speech self-supervised models: a compar- ative study,.

Input Conditioned Layer Dropping in Speech Foundation Models Fine-tuning strategies for faster in- ference using speech self-supervised models: a compar- ative study,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:16.121933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a905bab0-9e5d-4c95-bb83-b55f9039b894 · outbound

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

Input Conditioned Layer Dropping in Speech Foundation Models Training dynamic models using early exits for automatic speech recognition on resource-constrained devices

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:32:10.366066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8873f0ac-b715-4273-a515-3c4cf594307d · outbound

This paper cites Deep networks with stochastic depth,.

Input Conditioned Layer Dropping in Speech Foundation Models Deep networks with stochastic depth,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:15.987443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a86e6256-a265-4a3d-9468-2a41d3fc78e3 · outbound

This paper cites SkipNet: Learning dynamic routing in convolutional networks,.

Input Conditioned Layer Dropping in Speech Foundation Models SkipNet: Learning dynamic routing in convolutional networks,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:15.804043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 901d82dc-353c-45e3-8999-866c2419a16b · outbound

This paper cites Reducing transformer depth on de- mand with structured dropout,.

Input Conditioned Layer Dropping in Speech Foundation Models Reducing transformer depth on de- mand with structured dropout,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:15.631948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b2f0b61b-d39c-4884-a3bf-719ebb1bb03c · outbound

This paper cites On the effect of dropping layers of pre-trained transformer models,.

Input Conditioned Layer Dropping in Speech Foundation Models On the effect of dropping layers of pre-trained transformer models,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:15.269623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8ed81a5f-547c-4e94-a901-e59dff41516f · outbound

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

Input Conditioned Layer Dropping in Speech Foundation Models WavLM: Large-scale self- supervised pre-training for full stack speech process- ing,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:15.095753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 29918fc9-3f87-4ed1-9509-57eade41684e · outbound

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

Input Conditioned Layer Dropping in Speech Foundation Models LDASR: An experimental study on layer drop using conformer-based architecture,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:14.930976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8e83fda6-88f2-41bd-9971-b66ea2675f4a · outbound

This paper cites Convolutional Networks with Adaptive Inference Graphs,.

Input Conditioned Layer Dropping in Speech Foundation Models Convolutional Networks with Adaptive Inference Graphs,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:14.792379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1f37d52b-5c38-445f-86ad-a6f2066ebdd9 · outbound

This paper cites I3D: Transformer architectures with input-dependent dynamic depth for speech recognition,.

Input Conditioned Layer Dropping in Speech Foundation Models I3D: Transformer architectures with input-dependent dynamic depth for speech recognition,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:14.635583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 85eb8d58-69dd-48fb-9e6c-bd52ed5f0898 · outbound

This paper cites AST: Audio spectrogram trans- former,.

Input Conditioned Layer Dropping in Speech Foundation Models AST: Audio spectrogram trans- former,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:14.470399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f4b356ee-2363-45fb-87ef-038828d895e2 · outbound

This paper cites Squeeze-and-Excitation Networks,.

Input Conditioned Layer Dropping in Speech Foundation Models Squeeze-and-Excitation Networks,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:14.270689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7097ac97-f852-4946-ae52-28d35ccb43e3 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with simple and efficient spar- sity,.

Input Conditioned Layer Dropping in Speech Foundation Models Switch transformers: Scaling to trillion parameter models with simple and efficient spar- sity,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:14.074176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0c11495d-f462-46bb-bbc3-85854eec5e17 · outbound

This paper cites Adaptive mixtures of local ex- perts,.

Input Conditioned Layer Dropping in Speech Foundation Models Adaptive mixtures of local ex- perts,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:13.927615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 459ebc2e-dd4e-4f16-b1ff-80304c4cc06b · outbound

This paper cites Dynamic neural networks: A survey,.

Input Conditioned Layer Dropping in Speech Foundation Models Dynamic neural networks: A survey,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:13.723541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0ff9011d-35e7-4ff9-ae94-55eed34ed1c1 · outbound

This paper cites Deep residual learning for image recognition,.

Input Conditioned Layer Dropping in Speech Foundation Models Deep residual learning for image recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:13.549081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b451474e-0eb8-4d49-a1d4-436e867ac9f7 · outbound

This paper cites Attention is all you need,.

Input Conditioned Layer Dropping in Speech Foundation Models Attention is all you need,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:13.416203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 58fa47bd-bb83-47fc-bb4d-043c9201604c · outbound

This paper cites BlockDrop: Dynamic inference paths in residual networks,.

Input Conditioned Layer Dropping in Speech Foundation Models BlockDrop: Dynamic inference paths in residual networks,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:13.214674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 50823707-2d4f-4f9c-9b57-d70ccc445061 · outbound

This paper cites You look twice: Gaternet for dynamic filter selection in cnns,.

Input Conditioned Layer Dropping in Speech Foundation Models You look twice: Gaternet for dynamic filter selection in cnns,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:13.033101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 36524230-fa2b-4d5f-bb9d-04489128ef66 · outbound

This paper cites Stop or forward: Dynamic layer skipping for efficient action recognition,.

Input Conditioned Layer Dropping in Speech Foundation Models Stop or forward: Dynamic layer skipping for efficient action recognition,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:12.766635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7fa74a84-b981-4d6a-8681-2569be8019d5 · outbound

This paper cites Dual dynamic inference: Enabling more efficient, adaptive, and controllable deep infer- ence,.

Input Conditioned Layer Dropping in Speech Foundation Models Dual dynamic inference: Enabling more efficient, adaptive, and controllable deep infer- ence,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:12.500126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e1cddd06-9e3c-46a3-b8e3-8ba9f1781ff9 · outbound

This paper cites Fully dynamic inference with deep neural networks,.

Input Conditioned Layer Dropping in Speech Foundation Models Fully dynamic inference with deep neural networks,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:12.318977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bc2ec3bf-b8a5-4664-83de-1e77028cb25d · outbound

This paper cites Dynamic encoder size based on data- driven layer-wise pruning for speech recognition,.

Input Conditioned Layer Dropping in Speech Foundation Models Dynamic encoder size based on data- driven layer-wise pruning for speech recognition,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:12.187326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 48446f4c-f728-4f30-9164-7840e7bef5f4 · outbound

This paper cites Connectionist temporal classifica- tion: labelling unsegmented sequence data with recur- rent neural networks,.

Input Conditioned Layer Dropping in Speech Foundation Models Connectionist temporal classifica- tion: labelling unsegmented sequence data with recur- rent neural networks,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:11.973217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0303e4a0-dd0c-4009-b5ef-a194c1c18943 · outbound

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

Input Conditioned Layer Dropping in Speech Foundation Models Librispeech: an asr corpus based on public domain audio books,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:11.743681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a1e14213-7f5e-4b71-95ff-2d5795de9f0d · outbound

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

Input Conditioned Layer Dropping in Speech Foundation Models TED-LIUM 3: Twice as much data and corpus repartition for experiments on speaker adaptation,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:11.511102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e2d18b6e-92d1-4cbb-b760-d7dec8a366d4 · outbound

This paper cites ESC: Dataset for Environmental Sound Classification,.

Input Conditioned Layer Dropping in Speech Foundation Models ESC: Dataset for Environmental Sound Classification,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:11.256829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7e2bdea3-c2b8-4feb-9ad2-e2b8aa015961 · outbound

This paper cites Speech model pre-training for end-to-end spoken language understanding,.

Input Conditioned Layer Dropping in Speech Foundation Models Speech model pre-training for end-to-end spoken language understanding,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:11.054931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e6bdb5f9-7863-45b3-9de3-159c70630303 · outbound

This paper cites IEMOCAP: Interactive emotional dyadic motion capture database,.

Input Conditioned Layer Dropping in Speech Foundation Models IEMOCAP: Interactive emotional dyadic motion capture database,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:10.866952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1640dc7c-8d5e-409c-9e6f-92979e1bd3be · outbound

This paper cites SpecAugment: A simple data augmentation method for automatic speech recogni- tion,.

Input Conditioned Layer Dropping in Speech Foundation Models SpecAugment: A simple data augmentation method for automatic speech recogni- tion,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:32:10.711942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 068438fe-3d1c-439c-af4e-80019f1c267a · inbound