Paper Citation Record · LEDGER

Early Attentive Sparsification Accelerates Neural Speech Transcription

As of 8 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 1 inbound Pith citation observation for arXiv:2506.15912.

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

pith.paper-citation-record.v1
2506.15912 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:50:42.272617Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T17:06:02.978205Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-28T17:12:25.094606Z

Reference resolution

24 of 24 outbound references displayed

verified exact0
verified fuzzy8
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 26ce869f-231e-499e-bdd1-b62011b308c2 · outbound

This paper cites write newline.

Early Attentive Sparsification Accelerates Neural Speech Transcription write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:39.956510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e84de91-8dc8-4294-ac93-0fb066ed728f · outbound

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

Early Attentive Sparsification Accelerates Neural Speech Transcription Robust speech recognition via large-scale weak supervision

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:40.073181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83cdc81e-a577-44c0-bde0-e5cdcbd47554 · outbound

This paper cites Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks.

Early Attentive Sparsification Accelerates Neural Speech Transcription Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:42.831913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2a67118d-367b-40d9-b616-412eceffdb5c · outbound

This paper cites Deep speech 2: End-to-end speech recognition in english and mandarin.

Early Attentive Sparsification Accelerates Neural Speech Transcription Deep speech 2: End-to-end speech recognition in english and mandarin

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:42.813926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c4b9d66e-34a6-4e9e-b97f-70bc1ae30a98 · outbound

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

Early Attentive Sparsification Accelerates Neural Speech Transcription wav2vec 2.0: A framework for self-supervised learning of speech representations

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:40.347475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76fd6c3b-5e62-4340-8099-bf6eacd65f1a · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.

Early Attentive Sparsification Accelerates Neural Speech Transcription H2o: Heavy-hitter oracle for efficient generative inference of large language models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:42.784989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 997644ed-6095-45ef-96f6-424797a9b466 · outbound

This paper cites Q-hitter: A better token oracle for efficient llm inference via sparse-quantized kv cache.

Early Attentive Sparsification Accelerates Neural Speech Transcription Q-hitter: A better token oracle for efficient llm inference via sparse-quantized kv cache

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:42.767720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 90cf1147-ac60-4bd3-b0d5-59968017aac5 · outbound

This paper cites Spatten: Efficient sparse attention architecture with cascade token and head pruning.

Early Attentive Sparsification Accelerates Neural Speech Transcription Spatten: Efficient sparse attention architecture with cascade token and head pruning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:42.750698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e89276de-cf28-4e7f-998a-c29f91b6ca33 · outbound

This paper cites Attention is all you need.

Early Attentive Sparsification Accelerates Neural Speech Transcription Attention is all you need

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:40.692918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15e63d53-68e7-448a-aa24-e66523c58420 · outbound

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

Early Attentive Sparsification Accelerates Neural Speech Transcription Hubert: Self-supervised speech representation learning by masked prediction of hidden units

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:40.794663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd3bdc37-5bfa-46be-97da-aca0e8db58c3 · outbound

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

Early Attentive Sparsification Accelerates Neural Speech Transcription Librispeech: An asr corpus based on public domain audio books

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:40.864178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95397d90-3010-4bef-8bdb-cc5a507f6417 · outbound

This paper cites Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages.

Early Attentive Sparsification Accelerates Neural Speech Transcription Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:40.931247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32741414-4479-4748-b02d-4f9087946950 · outbound

This paper cites Anatomy of Industrial Scale Multilingual ASR.

Early Attentive Sparsification Accelerates Neural Speech Transcription Anatomy of Industrial Scale Multilingual ASR

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:41.036372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9f662a8-0597-4ae8-9df8-e171d0b0d4d2 · outbound

This paper cites Conformer: Convolution-augmented Transformer for Speech Recognition.

Early Attentive Sparsification Accelerates Neural Speech Transcription Conformer: Convolution-augmented Transformer for Speech Recognition

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:41.136057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a1b4535-e985-4949-a607-69efe96e2106 · outbound

This paper cites Fast conformer with linearly scalable attention for efficient speech recognition.

Early Attentive Sparsification Accelerates Neural Speech Transcription Fast conformer with linearly scalable attention for efficient speech recognition

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:42.712311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 14f26328-9095-4d51-b5f5-7559eb1cf5a4 · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

Early Attentive Sparsification Accelerates Neural Speech Transcription Sequence Transduction with Recurrent Neural Networks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:41.251767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c1766b8-510a-49ff-ae85-94215d4d34e1 · outbound

This paper cites Rnn-transducer with stateless prediction network.

Early Attentive Sparsification Accelerates Neural Speech Transcription Rnn-transducer with stateless prediction network

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:42.696003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8af9b248-f005-44d7-92dd-4316206f3101 · outbound

This paper cites Pruned RNN-T for fast, memory-efficient ASR training.

Early Attentive Sparsification Accelerates Neural Speech Transcription Pruned RNN-T for fast, memory-efficient ASR training

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:41.514296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d614886-8b84-4d78-b17f-4fe27420b3be · outbound

This paper cites End-to-end speech recognition: A survey.

Early Attentive Sparsification Accelerates Neural Speech Transcription End-to-end speech recognition: A survey

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:41.682676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f0a47e-1010-49be-bcdc-91741a049313 · outbound

This paper cites Revisiting convolution-free transformer for speech recognition.

Early Attentive Sparsification Accelerates Neural Speech Transcription Revisiting convolution-free transformer for speech recognition

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:42.667695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 85b300a6-aef3-41b2-9a6f-a8d16749ac7f · outbound

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

Early Attentive Sparsification Accelerates Neural Speech Transcription Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:41.917000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 879b87ea-8624-420a-b173-b84d76cdc715 · outbound

This paper cites Open automatic speech recognition leaderboard.

Early Attentive Sparsification Accelerates Neural Speech Transcription Open automatic speech recognition leaderboard

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:42.065387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a56947a-7a5e-4744-b517-e26ea3759166 · outbound

This paper cites LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation.

Early Attentive Sparsification Accelerates Neural Speech Transcription LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:42.212436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8941e34a-217b-4d57-a048-60a501fed8a9 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

Early Attentive Sparsification Accelerates Neural Speech Transcription FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:42.272617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 3bcdc5c7-b931-4a93-be1d-fcedcbffbd8b · inbound

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

MURMUR: An Efficient Inference System for Long-Form ASR Early Attentive Sparsification Accelerates Neural Speech Transcription

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:12:25.096232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.