Paper Citation Record · LEDGER

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications

As of 18 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 4 inbound Pith citation observations for arXiv:2507.16456.

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

pith.paper-citation-record.v1
2507.16456 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:13:09.466878Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:13:09.248765Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T12:29:52.151460Z

Reference resolution

29 of 29 outbound references displayed

verified exact1
verified fuzzy14
unresolved13
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4e872ef7-38bf-4dfc-9568-8a1eac64559a · outbound

This paper cites Significant ad- vancements in the field have led to increasingly accurate mod- els, some of which even surpass human-level performance [1].

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Significant ad- vancements in the field have led to increasingly accurate mod- els, some of which even surpass human-level performance [1]

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.898863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3e96ae6e-a6dd-4dc3-9883-150082a954fc · outbound

This paper cites An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications

Reference 2

Resolution: malformed identifier; no resolver link, observed 2026-08-06T15:13:09.248765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b847f942-74c7-4d37-af88-2f812c3c115d · outbound

This paper cites Our goal is to explore the potential of LLMs by systemati- cally evaluating multiple models across a diverse set of English- language datasets.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Our goal is to explore the potential of LLMs by systemati- cally evaluating multiple models across a diverse set of English- language datasets

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.885117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ea7c2da0-f903-4811-bcc7-6bff4c363b40 · outbound

This paper cites Specifically, we used 645 ut- terances from Fleurs, 245 utterances from V oxPopuli, and 250 utterances from Librispeech, all in English.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Specifically, we used 645 ut- terances from Fleurs, 245 utterances from V oxPopuli, and 250 utterances from Librispeech, all in English

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.871471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f73c384d-581b-49d6-9993-edfc148373b7 · outbound

This paper cites As expected, the performance of ASR improves with an increase in the number of parameters in models that use the same backend architec- ture.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications As expected, the performance of ASR improves with an increase in the number of parameters in models that use the same backend architec- ture

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.858582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b73d0504-ff3a-44ce-932d-141be8f07446 · outbound

This paper cites Extending this analysis to multiple LLMs would be useful to better understand the overall trends across different models.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Extending this analysis to multiple LLMs would be useful to better understand the overall trends across different models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.845525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4874c60b-e528-4e74-90d4-4305f9b8af8f · outbound

This paper cites an unresolved cited work.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:13:09.832763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 02004802-0d92-4439-80af-79d01a71e517 · outbound

This paper cites The microsoft 2017 conversational speech recognition system,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications The microsoft 2017 conversational speech recognition system,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.819804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 74c2ec40-49c4-43c0-8bd9-8c829f3094c0 · outbound

This paper cites Improving automatic speech recogni- tion performance for low-resource languages with self-supervised models,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Improving automatic speech recogni- tion performance for low-resource languages with self-supervised models,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.388608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0286974f-39a2-4edf-ab0a-22181c66313a · outbound

This paper cites Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.392483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 609074f2-ed89-4144-86e5-efa1ce6966d5 · outbound

This paper cites Semantic word error rate for sentence similarity,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Semantic word error rate for sentence similarity,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.797148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f42a3bff-6721-4b0a-b99a-46d52b3b47a9 · outbound

This paper cites From WER and RIL to MER and WIL: improved evaluation measures for connected speech recognition.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications From WER and RIL to MER and WIL: improved evaluation measures for connected speech recognition

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.400437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0ef268c-204f-46aa-adf3-32359ab04bee · outbound

This paper cites BERTScore: Evaluating Text Generation with BERT.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications BERTScore: Evaluating Text Generation with BERT

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.404909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc6ae7b2-9592-40f5-9380-621d98f5a341 · outbound

This paper cites A Comprehensive Overview of Large Language Models.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications A Comprehensive Overview of Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.409114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a854f95-5ce1-48fb-b755-633625cf7b6a · outbound

This paper cites Investigating ASR error correction with large language model and multilingual 1-best hypotheses,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Investigating ASR error correction with large language model and multilingual 1-best hypotheses,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.774415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a1a06338-293a-42e0-a3be-72a526a10d82 · outbound

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

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications An Embarrassingly Simple Approach for LLM with Strong ASR Capacity

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.416457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 883d3c6d-7c11-4b9c-93cb-5684c2c3e29e · outbound

This paper cites Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-06T15:13:09.597831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e5ed13b0-04bd-4322-9d51-1afc668d7b1b · outbound

This paper cites Lexical error guard: Lever- aging large language models for enhanced ASR error correction,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Lexical error guard: Lever- aging large language models for enhanced ASR error correction,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.758167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 24aaadf6-36c6-4a5c-81e6-1d893ba8272e · outbound

This paper cites Can Generative Large Language Models Perform ASR Error Correction?.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Can Generative Large Language Models Perform ASR Error Correction?

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.428068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ea00a31-6183-486f-b393-c733cc9d97b4 · outbound

This paper cites Leveraging large language models for exploiting ASR un- certainty,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Leveraging large language models for exploiting ASR un- certainty,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.742000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 592a58ea-645d-4877-bc96-b368e014cbf6 · outbound

This paper cites Fleurs: Few-shot learning evaluation of universal representations of speech,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Fleurs: Few-shot learning evaluation of universal representations of speech,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.727024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6404bd70-32fa-466e-b654-406b91370c41 · outbound

This paper cites VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.439905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc3e50d9-d4fa-4871-9b88-d99d67913dec · outbound

This paper cites Lib- rispeech: an ASR corpus based on public domain audio books,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Lib- rispeech: an ASR corpus based on public domain audio books,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.712806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2e0b1fb3-7baf-474a-a49a-39a4be26e7f6 · outbound

This paper cites Whisper: A general-purpose speech recognition model,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Whisper: A general-purpose speech recognition model,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.698636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 051b200f-dc38-4ad3-af81-c50fcaee42d9 · outbound

This paper cites wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.451024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e00af6c-4169-41d1-bc7c-c9621d70da46 · outbound

This paper cites GPT-4 Technical Report.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications GPT-4 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.455316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0863c203-1742-4110-9921-7dcf687b0482 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.459199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5b52ec7-1165-4244-aa28-deeb7bb0beae · outbound

This paper cites Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T15:13:09.462815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0131f658-34fb-4293-9f0f-bd9d0ff45bf9 · outbound

This paper cites Berkeley function calling leader- board,.

An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications Berkeley function calling leader- board,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:13:09.684966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 3e96ae6e-a6dd-4dc3-9883-150082a954fc · inbound