Paper Citation Record · LEDGER

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings

As of 18 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 2 inbound Pith citation observations for arXiv:2509.04473.

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

pith.paper-citation-record.v1
2509.04473 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:53:26.333669Z

measured 38 of 38 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:28:35.227309Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T13:53:27.421561Z

Reference resolution

36 of 36 outbound references displayed

verified exact4
verified fuzzy10
unresolved20
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4410ef93-6f9e-4d03-9ab9-5cba25ec4f97 · outbound

This paper cites SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:53:27.462666Z

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 a3952895-eef2-48ee-b920-228e158814c9 · outbound

This paper cites an unresolved cited work.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:53:30.674755Z

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 885256b4-b595-4d76-b1f4-82e21a0f4955 · outbound

This paper cites The ASR baseline benchmarks on the Librispeech dataset are derived from the study in [5], which is similar to ours but focuses solely on ASR.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings The ASR baseline benchmarks on the Librispeech dataset are derived from the study in [5], which is similar to ours but focuses solely on ASR

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T13:53:30.449286Z

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 732f7e07-3f18-4a56-993b-d8257f0d5638 · outbound

This paper cites We conduct the SA training for 50 epochs with a learning rate 5 ∗ 10−4, batch size 6, and a linear decay scheduler with 3000 warm-up steps.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings We conduct the SA training for 50 epochs with a learning rate 5 ∗ 10−4, batch size 6, and a linear decay scheduler with 3000 warm-up steps

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T13:53:30.190439Z

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 8e497bb1-3157-479a-ae62-01fb49703981 · outbound

This paper cites The proposed model exhibits the capability to capture semantic meanings by effectively mapping speech features to text tokens that are interpretable by LLMs.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings The proposed model exhibits the capability to capture semantic meanings by effectively mapping speech features to text tokens that are interpretable by LLMs

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:29.960854Z

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 72776b61-651b-458d-8e17-569f95cb25ea · outbound

This paper cites GPT-4 Technical Report.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings GPT-4 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:23.718934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d98b71f-fc12-4dc9-84ee-1643e5b8089a · outbound

This paper cites A survey on speech large language models,.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings A survey on speech large language models,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:23.783968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 781a65e3-df2f-4100-925e-febc9653236d · outbound

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

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Robust speech recognition via large-scale weak supervision,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:23.847695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a61053b5-c086-41dd-ac0d-63fe788e99da · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings TinyLlama: An Open-Source Small Language Model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:23.880279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a2508d2-110c-4be6-afcc-a424821966ce · outbound

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

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings An Embarrassingly Simple Approach for LLM with Strong ASR Capacity

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:23.962333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23427e32-03aa-4a5c-8c6e-7bfae1829283 · outbound

This paper cites SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:24.021157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c422d072-d248-469c-8148-e8c47a873d02 · outbound

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

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings SALMONN: Towards Generic Hearing Abilities for Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:24.084203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bdd7516-15ca-4c7b-b5c4-84026c4896c1 · outbound

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

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:24.131210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c6534f-ef50-4d68-aef2-43dc18d60de8 · outbound

This paper cites AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:24.189799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de92ddd5-55ca-4b6b-a812-dc0c72dacf23 · outbound

This paper cites ” i’ve heard of you!.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings ” i’ve heard of you!

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:29.676823Z

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 428a4dd6-40a7-4586-b460-2cf0ad19c3fb · outbound

This paper cites Whisper-slu: Ex- tending a pretrained speech-to-text transformer for low resource spoken language understanding,.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Whisper-slu: Ex- tending a pretrained speech-to-text transformer for low resource spoken language understanding,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:29.415213Z

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 50b75b74-679c-4de3-8a9b-7c016f811fb1 · outbound

This paper cites On the Evaluation of Speech Foundation Models for Spoken Language Understanding.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings On the Evaluation of Speech Foundation Models for Spoken Language Understanding

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:24.385057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7807b942-288e-4d33-8945-a4187e73c536 · outbound

This paper cites Universlu: Uni- versal spoken language understanding for diverse tasks with nat- ural language instructions,.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Universlu: Uni- versal spoken language understanding for diverse tasks with nat- ural language instructions,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:29.176460Z

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 cc3f337a-3a2d-429c-af5c-37935193ffbc · outbound

This paper cites Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language Understanding.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language Understanding

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:53:27.083579Z

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 9dbc050f-12ae-42f1-a78a-099bbe3d5e2b · outbound

This paper cites Salm: Speech- augmented language model with in-context learning for speech recognition and translation,.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Salm: Speech- augmented language model with in-context learning for speech recognition and translation,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:28.826670Z

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 9533b423-310a-49f5-a200-f934b58dbf2c · outbound

This paper cites WhisperNER: Unified Open Named Entity and Speech Recognition.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings WhisperNER: Unified Open Named Entity and Speech Recognition

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:53:26.920380Z

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 3808f0ce-1201-4d6c-8054-6db1f7971421 · outbound

This paper cites Chinese asr and ner improvement based on whisper fine-tuning,.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Chinese asr and ner improvement based on whisper fine-tuning,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:28.546140Z

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 388e7e80-4436-4167-a6df-e22a9740a22f · outbound

This paper cites NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:24.614481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9ac977e-bbb2-4630-b908-0fa832ec4f78 · outbound

This paper cites Using Large Language Model for End-to-End Chinese ASR and NER.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Using Large Language Model for End-to-End Chinese ASR and NER

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:53:26.745129Z

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 9bf4cc41-8be5-499a-ab66-a0aa23b369a8 · outbound

This paper cites WavLLM: Towards Robust and Adaptive Speech Large Language Model.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings WavLLM: Towards Robust and Adaptive Speech Large Language Model

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:24.835833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aad7e48-dc54-4584-ae1d-e9607bda13ee · outbound

This paper cites End-to-end Named Entity Recognition from English Speech.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings End-to-end Named Entity Recognition from English Speech

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:24.953794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f73a246-f793-410c-b515-54f69c5432dd · outbound

This paper cites End-to-end named entity and semantic concept extraction from speech,.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings End-to-end named entity and semantic concept extraction from speech,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:28.260325Z

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 ab6ef9c1-2eb4-42b7-a572-417e22a4c48c · outbound

This paper cites Slue: New benchmark tasks for spoken language un- derstanding evaluation on natural speech,.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Slue: New benchmark tasks for spoken language un- derstanding evaluation on natural speech,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:27.940309Z

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 0c5dcb25-d6a4-4dd0-a158-e93b099c9ebe · outbound

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

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Lib- rispeech: an asr corpus based on public domain audio books,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:27.780738Z

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 1d292078-0891-4d23-92c2-4d347df25a3b · outbound

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

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:25.480535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85ece306-a343-488d-9b0b-d834a17db7bc · outbound

This paper cites VoxCeleb: a large-scale speaker identification dataset.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings VoxCeleb: a large-scale speaker identification dataset

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:25.645970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3972282-9234-49b3-8c18-48c3e205d0be · outbound

This paper cites Ontonotes: the 90% solution,.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Ontonotes: the 90% solution,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:53:27.633245Z

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 d8ada98e-7101-41aa-bc65-6b30936d052a · outbound

This paper cites PromptNER: Prompting For Named Entity Recognition.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings PromptNER: Prompting For Named Entity Recognition

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:25.913786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b98be2c8-d21e-49a4-9458-0ff433743321 · outbound

This paper cites Specaugment: A simple data augmentation method for automatic speech recognition,.

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Specaugment: A simple data augmentation method for automatic speech recognition,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:26.053496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c6d5fb-6e01-442b-b1ff-ec02188ae659 · outbound

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

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:26.205888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0a3bb6a-f4c9-4e8b-8947-8f08906babb4 · outbound

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

SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings Hubert: Self-supervised speech represen- tation learning by masked prediction of hidden units,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T13:53:26.333669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4410ef93-6f9e-4d03-9ab9-5cba25ec4f97 · inbound