Paper Citation Record · LEDGER

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding

As of 20 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2507.18181.

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

pith.paper-citation-record.v1
2507.18181 v2

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:42:56.200787Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

35 of 35 outbound references displayed

verified exact1
verified fuzzy4
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation de92f81f-faf7-44ac-90ec-95207624deb4 · outbound

This paper cites GPT-4 Technical Report.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:55.990819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e04d542-8800-423e-bdfc-69de61ad0d76 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding LLaMA: Open and Efficient Foundation Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:55.998668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01e6fea3-b51b-4b12-930c-720a8b173426 · outbound

This paper cites Toolqa: A dataset for llm question answering with external tools,.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Toolqa: A dataset for llm question answering with external tools,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:42:56.909740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1c4b2c8a-fd7c-4f30-8c15-462075c4fce3 · outbound

This paper cites RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.011964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc724691-917e-4c1d-8afa-cf06cafa5ba3 · outbound

This paper cites On decoder-only architecture for speech-to-text and large language model integration,.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding On decoder-only architecture for speech-to-text and large language model integration,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:42:56.886571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 21734548-2019-4bc3-8084-296e92507613 · outbound

This paper cites Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.029693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b80dc020-9196-44e7-8b93-c1503b356253 · outbound

This paper cites Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.037314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65f20b7f-5213-4063-be88-bbe4978d02b0 · outbound

This paper cites LLaMA-Omni: Seamless Speech Interaction with Large Language Models.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.043822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e729f6ac-1491-41e4-a5c7-18a9eca2124d · outbound

This paper cites Prompting large language models with speech recognition abilities,.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Prompting large language models with speech recognition abilities,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.050084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daa9695a-152c-4faf-8abb-2599c78ae90b · outbound

This paper cites BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.055144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbf8372b-7af9-4290-8c7a-f53c317d8c70 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.060549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdc72fae-8afb-4ddc-85bb-e7e56106503a · outbound

This paper cites Fast inference from transform- ers via speculative decoding,.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Fast inference from transform- ers via speculative decoding,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:42:56.854937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 24d2f468-67f1-4805-841e-a7bdb2402af4 · outbound

This paper cites SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.072232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08d9a2c0-da64-4c02-ad38-d3f62d74b9d7 · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.078104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88326143-65d3-4c93-a2f4-f6479bdf695e · outbound

This paper cites EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.083727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1f4f612-a7f2-423b-97f4-69f78366719e · outbound

This paper cites DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.088831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b228948d-24cb-4c9a-b9f9-dfd6464a26e7 · outbound

This paper cites Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.099285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a12db20-3fba-404d-9755-e144de931249 · outbound

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

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.105526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 581e39d2-a2e8-4a33-9fa6-4007ec3be640 · outbound

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

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Conformer: Convolution-augmented Transformer for Speech Recognition

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.113650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a270a48d-e080-4856-923d-6cb749901da6 · outbound

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

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Robust speech recognition via large-scale weak supervi- sion,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.119922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48df1ca7-cf0c-4c7f-a01b-8286b5a3a499 · outbound

This paper cites Qwen Technical Report.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Qwen Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.125624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05d14811-e291-4952-8b7b-2341e71d1cb7 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding LoRA: Low-Rank Adaptation of Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.131841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3fbdefc-9124-4558-89b6-5747d771b5c1 · outbound

This paper cites ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:42:56.437339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f31eb41e-0fe5-4dab-ae74-66c0b9170f8a · outbound

This paper cites EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.143024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b5560ce-9c21-4436-92ab-f9fec4d89794 · outbound

This paper cites Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.148559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edb5eac1-7dd3-4861-8030-aa164879a2ae · outbound

This paper cites Multi-Candidate Speculative Decoding.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Multi-Candidate Speculative Decoding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.153661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 383dba0e-d0a1-48d7-87a9-4c55d2562b42 · outbound

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

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Librispeech: an asr corpus based on public domain audio books,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.158384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd4ce433-0015-48b5-b528-4c77f79762c4 · outbound

This paper cites LRS3-TED: a large-scale dataset for visual speech recognition.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding LRS3-TED: a large-scale dataset for visual speech recognition

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.162477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4c2cbb7-5402-430d-9009-72f954f1f126 · outbound

This paper cites ParallelSpec: Parallel Drafter for Efficient Speculative Decoding.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding ParallelSpec: Parallel Drafter for Efficient Speculative Decoding

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.168146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db89456a-46ca-419a-a6a3-98af10f03b63 · outbound

This paper cites Online Speculative Decoding.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Online Speculative Decoding

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.172945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6c432d6-0893-4a3b-98f2-74ff3dd8867c · outbound

This paper cites Spectr: Fast speculative decoding via optimal transport,.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Spectr: Fast speculative decoding via optimal transport,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.178146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a754c70-49bc-4b8d-a26a-8e6d231d0cbf · outbound

This paper cites Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.183295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9faaa76d-0b1c-4be5-b78f-4da91433aea4 · outbound

This paper cites Recurrent Drafter for Fast Speculative Decoding in Large Language Models.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Recurrent Drafter for Fast Speculative Decoding in Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.188422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cb39e25-dfa2-4929-866e-acc0dc1c65e7 · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023,.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:42:56.801696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6ac5c690-1150-4e61-b0fd-60d81021b3ca · outbound

This paper cites An Embarrassingly Simple Approach for LLM with Strong ASR Capacity.

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding An Embarrassingly Simple Approach for LLM with Strong ASR Capacity

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T14:42:56.200787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.