Paper Citation Record · LEDGER

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation

As of 11 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2607.08117.

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

pith.paper-citation-record.v1
2607.08117 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-10T12:48:18.738249Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-10T12:48:18.738249Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T12:57:07.673047Z

Reference resolution

35 of 35 outbound references displayed

verified exact5
verified fuzzy26
unresolved2
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4d22c1a6-308d-46a8-9b88-f4d2ac1c7c30 · outbound

This paper cites COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-10T12:57:07.674338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9cc91b8b-4523-4b3d-95d3-dd3c0b435beb · outbound

This paper cites an unresolved cited work.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-07-10T12:57:08.013292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c4b7ff85-6541-4983-b3fe-d720ac24731d · outbound

This paper cites Datasets We evaluate our proposed method on the LibriSpeech corpus [18], following the contextual biasing experimental setup es- tablished in prior study [19].

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Datasets We evaluate our proposed method on the LibriSpeech corpus [18], following the contextual biasing experimental setup es- tablished in prior study [19]

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-07-10T12:57:07.977282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 11541ae2-6a82-4318-bd91-69edafa5c461 · outbound

This paper cites The Performance of Biasing Scoring Table 1 compares the performance of biasing scoring across dif- ferent objectives.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation The Performance of Biasing Scoring Table 1 compares the performance of biasing scoring across dif- ferent objectives

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.979161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ab713b08-9f95-40ef-9346-8f5570ad41b0 · outbound

This paper cites Notably, DPD-Loss achieves a Recall#20 of 99.09% on test-clean, signifying that target entities are al- most invariably ranked within the top-20 candidates.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Notably, DPD-Loss achieves a Recall#20 of 99.09% on test-clean, signifying that target entities are al- most invariably ranked within the top-20 candidates

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.983070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 783dd15a-f484-45ca-a583-1645929a9fe7 · outbound

This paper cites The COALA is optimized via DPD-Loss.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation The COALA is optimized via DPD-Loss

Reference 6

Resolution: malformed identifier; raw_fallback, observed 2026-07-10T12:57:07.985143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 582d6baf-db0e-44ba-ba69-a98a0e9d5bb0 · outbound

This paper cites an unresolved cited work.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-07-10T12:57:08.007985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ca66059a-3751-4819-bd3e-9e5fd3f1c5a6 · outbound

This paper cites Any findings and implications in the paper do not necessarily reflect those of the sponsors.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Any findings and implications in the paper do not necessarily reflect those of the sponsors

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.011686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 806caa08-7519-4663-8eac-2a69b917bcfe · outbound

This paper cites We maintained full control over the re- search content and remain responsible for the accuracy and in- tegrity of the experimental results and the presented figures.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation We maintained full control over the re- search content and remain responsible for the accuracy and in- tegrity of the experimental results and the presented figures

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.004259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 15909d70-8f9c-4e90-8db0-73aca906e0b7 · outbound

This paper cites Con- nectionist temporal classification: labelling unsegmented se- quence data with recurrent neural networks,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Con- nectionist temporal classification: labelling unsegmented se- quence data with recurrent neural networks,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.006082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 55e30e99-9839-4a25-93cb-360bbe46f0d8 · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Sequence Transduction with Recurrent Neural Networks

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-10T12:57:07.669397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f1c2fff0-2b9c-4eb7-b637-b4db28885381 · outbound

This paper cites Neural machine translation by jointly learning to align and translate,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Neural machine translation by jointly learning to align and translate,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.020731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ee7a3cf1-5098-4d32-a855-a06f791ae137 · outbound

This paper cites Hybrid transducer and attention based encoder-decoder modeling for speech-to-text tasks,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Hybrid transducer and attention based encoder-decoder modeling for speech-to-text tasks,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.997101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2a7b53f8-8fa3-43c9-8d76-d6edcd89a459 · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-10T12:57:07.667044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4cf2ba07-23f1-4ea3-aeba-fb9f00f0e4b2 · outbound

This paper cites SALMONN: Towards Generic Hearing Abilities for Large Language Models.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation SALMONN: Towards Generic Hearing Abilities for Large Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-10T12:57:07.664542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f0cc6a09-0d85-4f9d-99de-be13c0e2b105 · outbound

This paper cites Qwen2-Audio Technical Report.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Qwen2-Audio Technical Report

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-10T12:57:07.671793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7eaf9504-7240-43cb-990e-e595985dc562 · outbound

This paper cites Prepending or cross-attention for speech-to-text? an empirical comparison,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Prepending or cross-attention for speech-to-text? an empirical comparison,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.000623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 82c37faa-ed7a-4a55-954c-85838a9c1455 · outbound

This paper cites Wavllm: Towards robust and adap- tive speech large language model,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Wavllm: Towards robust and adap- tive speech large language model,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.002457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d964c8d6-2ce5-4da9-82aa-6d44b62ddbf3 · outbound

This paper cites Weighted finite-state trans- ducers in speech recognition,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Weighted finite-state trans- ducers in speech recognition,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.017106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 24a02fba-f5ec-4e50-beaf-67149a13b706 · outbound

This paper cites Shallow-fusion end-to-end contextual biasing.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Shallow-fusion end-to-end contextual biasing

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.988869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 85fa7cd9-5faa-4858-9996-f775fd41edf1 · outbound

This paper cites Contextual speech recognition in end-to-end neural net- work systems using beam search.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Contextual speech recognition in end-to-end neural net- work systems using beam search

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.993411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fb1e0784-652a-4fe9-a204-fb7c5536c826 · outbound

This paper cites A neural model for contextual biasing score learning and filtering,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation A neural model for contextual biasing score learning and filtering,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.991579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8bccc462-2e2f-4d06-8dc8-8ac12af43069 · outbound

This paper cites Contextual adapters for personalized speech recognition in neural transducers.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Contextual adapters for personalized speech recognition in neural transducers

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.998819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a52a49f7-06b1-4af9-ba26-b6d5cbe9d0d4 · outbound

This paper cites Retrieve and copy: Scaling asr personalization to large catalogs,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Retrieve and copy: Scaling asr personalization to large catalogs,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.995258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 53382236-4e29-4bda-9bfd-873f685662da · outbound

This paper cites Minimising biasing word errors for contextual asr with the tree-constrained pointer gener- ator,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Minimising biasing word errors for contextual asr with the tree-constrained pointer gener- ator,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.015202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a142f164-134c-4a25-b0b4-ab68d8d36c9d · outbound

This paper cites Graph neural networks for contextual asr with the tree-constrained pointer generator,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Graph neural networks for contextual asr with the tree-constrained pointer generator,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.981096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation faf19e47-48de-4797-b376-c94508101258 · outbound

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

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Lib- rispeech: An asr corpus based on public domain audio books,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.024355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c92ca048-2bb1-407e-b504-4e8c4f943c4e · outbound

This paper cites Contextualized streaming end-to-end speech recognition with trie-based deep bi- asing and shallow fusion,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Contextualized streaming end-to-end speech recognition with trie-based deep bi- asing and shallow fusion,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.974967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7c7c5f5a-d5fd-471c-bd37-06b4630bc504 · outbound

This paper cites Ctc-assisted llm-based contextual asr,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Ctc-assisted llm-based contextual asr,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.987053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6d1d9006-f13c-4ad3-b95a-7f3d8d9e612f · outbound

This paper cites Knowledge prompt for whisper: An asr entity correction approach with knowledge base,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Knowledge prompt for whisper: An asr entity correction approach with knowledge base,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.018905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 39d288c4-1e77-41a0-9766-470887e55906 · outbound

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

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Robust speech recognition via large-scale weak su- pervision

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.009829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 93bede1f-1bd7-411a-8bcd-9565c2367fd8 · outbound

This paper cites Contextual biasing speech recognition in speech-enhanced large language model,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Contextual biasing speech recognition in speech-enhanced large language model,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:08.022539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a53b192f-76f4-4a00-995c-a16fa0ce6ae6 · outbound

This paper cites Contextualized end-to-end automatic speech recognition with intermediate bias- ing loss,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Contextualized end-to-end automatic speech recognition with intermediate bias- ing loss,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.969513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 70be0856-3f39-4378-a28f-4884187a6a2c · outbound

This paper cites Hy- brid ctc/attention architecture for end-to-end speech recognition,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Hy- brid ctc/attention architecture for end-to-end speech recognition,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.973044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0cf62f98-c7f3-42b4-82f0-54f8c67662cf · outbound

This paper cites Contextualized automatic speech recognition with attention- based bias phrase boosted beam search,.

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation Contextualized automatic speech recognition with attention- based bias phrase boosted beam search,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T12:57:07.971349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

Observation 4d22c1a6-308d-46a8-9b88-f4d2ac1c7c30 · inbound