Paper Citation Record · LEDGER

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition

As of 17 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2501.09258.

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

pith.paper-citation-record.v1
2501.09258 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:14:40.479138Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-21T23:34:52.249143Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T23:35:45.995297Z

Reference resolution

35 of 35 outbound references displayed

verified exact0
verified fuzzy26
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ceb45d18-e76e-44fb-a324-9327536b85fa · outbound

This paper cites GPT-4 Technical Report.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:40.327675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20130fd1-e4a7-4181-8025-979f0e4da704 · outbound

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

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition LLaMA: Open and Efficient Foundation Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:40.331831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99093c50-b18e-41fa-9af3-e58604b1f0e9 · outbound

This paper cites PaLM: Scal- ing language modeling with pathways,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition PaLM: Scal- ing language modeling with pathways,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.880922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9ee5b8f1-8d5b-40df-a711-23b45b313851 · outbound

This paper cites Mistral 7B.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Mistral 7B

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:40.339567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae350a6e-17f5-401e-898c-8eb38820969f · outbound

This paper cites Large Language Models: A Survey.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Large Language Models: A Survey

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:40.343504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d638c5-1294-46ef-a11f-f6d1d760894f · outbound

This paper cites Attention is all you need,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Attention is all you need,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.870941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 010d43b0-666c-4a66-93c4-76aacc2ac254 · outbound

This paper cites AudioPaLM: A Large Language Model That Can Speak and Listen.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition AudioPaLM: A Large Language Model That Can Speak and Listen

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:40.351545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf021003-c347-4368-a5f1-31d336ea97fc · outbound

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

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition On decoder-only architecture for speech-to-text and large language model integration,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.861122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7958c125-d744-40fa-b396-3ea0af39571a · outbound

This paper cites SALSA: Speedy asr- llm synchronous aggregation,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition SALSA: Speedy asr- llm synchronous aggregation,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.851502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ac33f144-1cd4-451e-aaee-127e012f67fd · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:40.361592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5b3f3a5-4570-42e0-abb3-817f2e1b3b36 · outbound

This paper cites OpenLLaMA: An open reproduction of LLaMA,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition OpenLLaMA: An open reproduction of LLaMA,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.841004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8b13a56f-cd01-4439-bf3e-f6f669b28b12 · outbound

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

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition End-to-end speech recognition: A survey,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:40.375634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a62dd26f-6dad-4c3b-b852-210403adb514 · outbound

This paper cites Advances in joint CTC- attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Advances in joint CTC- attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.824931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 052cd3ea-c45d-4016-8643-b022b9b3e586 · outbound

This paper cites A comparison of techniques for language model integration in encoder-decoder speech recognition,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition A comparison of techniques for language model integration in encoder-decoder speech recognition,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.815491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e1f286ac-f88c-4e53-8eb7-08701d5409c5 · outbound

This paper cites On language model integration for RNN transducer based speech recognition,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition On language model integration for RNN transducer based speech recognition,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.806170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d49e4993-79e6-4373-aa3f-fe896258c6e4 · outbound

This paper cites Cold fusion: Training seq2seq models together with language models,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Cold fusion: Training seq2seq models together with language models,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.796084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6cb89126-aa77-4ba9-9652-699142c53ee6 · outbound

This paper cites Simple fusion: Return of the language model,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Simple fusion: Return of the language model,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.785391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6b882b32-d7a7-406b-a87d-8eb22ddd1e68 · outbound

This paper cites Internal language model estimation for domain-adaptive end-to-end speech recognition,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Internal language model estimation for domain-adaptive end-to-end speech recognition,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.775109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9205d564-b9b6-41e9-b415-93132448e8ab · outbound

This paper cites Efficient WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Efficient WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.765198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3f8ebd03-a29e-4111-928d-1581ff0f7429 · outbound

This paper cites On-the-fly lattice rescoring for real- time automatic speech recognition,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition On-the-fly lattice rescoring for real- time automatic speech recognition,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.755660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 46843466-3788-44f9-be2e-ea833c9487ed · outbound

This paper cites First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:40.417816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce157d74-bc15-42f4-9652-f2720aac2553 · outbound

This paper cites End-to-end speech recognition with word-based RNN language models,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition End-to-end speech recognition with word-based RNN language models,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.745913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2a9ad25d-eec5-4190-8fb0-69b96f9daaa1 · outbound

This paper cites An Empirical Study of Efficient ASR Rescoring with Transformers.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition An Empirical Study of Efficient ASR Rescoring with Transformers

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:40.426698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecb3671a-1559-4edc-ad09-764810b02d3d · outbound

This paper cites RescoreBERT: Discriminative speech recognition rescoring with BERT,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition RescoreBERT: Discriminative speech recognition rescoring with BERT,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.735793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cc2d67f4-6c5f-48ec-a9e6-06106f7c1dbe · outbound

This paper cites Multilingual and fully non- autoregressive asr with large language model fusion: A comprehensive study,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Multilingual and fully non- autoregressive asr with large language model fusion: A comprehensive study,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.725708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation af4aed5a-a2c4-4729-ba2f-638c92f03eb8 · outbound

This paper cites Effect and analysis of large-scale language model rescoring on competitive asr systems,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Effect and analysis of large-scale language model rescoring on competitive asr systems,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.715515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 85fef19a-77fe-4e6d-8b99-20d123946f71 · outbound

This paper cites Generative speech recognition error correction with large language models and task-activating prompting,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Generative speech recognition error correction with large language models and task-activating prompting,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.705186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 63a79d0c-5858-4003-9ffa-b19891611465 · outbound

This paper cites N-best T5: Robust asr error correction using multiple input hypotheses and constrained decoding space,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition N-best T5: Robust asr error correction using multiple input hypotheses and constrained decoding space,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.695029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation aeb847bc-9731-40cb-ad4c-15e1660cebb4 · outbound

This paper cites Connectionist temporal classification: Labelling unsegmented sequence data with re- current neural networks,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Connectionist temporal classification: Labelling unsegmented sequence data with re- current neural networks,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.684026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0def526d-cb22-41b6-8385-fe66b1bd841a · outbound

This paper cites Sentencepiece: A simple and language inde- pendent subword tokenizer and detokenizer for neural text processing,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Sentencepiece: A simple and language inde- pendent subword tokenizer and detokenizer for neural text processing,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.673332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 58a34bb1-39a7-4266-9281-9509c03ecb46 · outbound

This paper cites Libriheavy: a 50,000 hours asr corpus with punctuation casing and context,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Libriheavy: a 50,000 hours asr corpus with punctuation casing and context,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.661728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0b160e55-5ae5-4615-b017-5ff4a07f8018 · outbound

This paper cites Hybrid CTC/attention architecture for end-to-end speech recognition,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Hybrid CTC/attention architecture for end-to-end speech recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.650686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 68e1319e-dce5-43d6-8a31-c0a252c192ad · outbound

This paper cites WeNet: Production oriented streaming and non- streaming end-to-end speech recognition toolkit,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition WeNet: Production oriented streaming and non- streaming end-to-end speech recognition toolkit,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.640600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8e3ed6b6-b44e-474b-8d64-ee72ccf96707 · outbound

This paper cites Joint CTC/attention decoding for end-to-end speech recognition,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Joint CTC/attention decoding for end-to-end speech recognition,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.629904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 34da047e-fe64-40bd-ab8e-2e48fa4f98c0 · outbound

This paper cites Sequence transduction with recurrent neural networks,.

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition Sequence transduction with recurrent neural networks,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:14:40.618771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation e6be21a0-8b88-4af3-b806-c34e4aef40ef · inbound

Non-Intrusive Automatic Speech Recognition Refinement: A Survey cites this paper.

Non-Intrusive Automatic Speech Recognition Refinement: A Survey Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:35:46.000621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.