Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition | Paper Citation Record

Observation 5a8dbb83-a896-4edb-9188-25e9b367387f · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Sequence Transduction with Recurrent Neural Networks

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:15.105989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce5d0abb-9462-499d-9853-6e2a7b64545d · outbound

This paper cites End-to-end attention-based large vocabulary speech recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition End-to-end attention-based large vocabulary speech recognition,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:19.287405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 70d3288e-6b11-4ddc-883d-ac9529e32046 · outbound

This paper cites Listen, attend and spell: A neural network for large vocabulary conversational speech recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Listen, attend and spell: A neural network for large vocabulary conversational speech recognition,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:19.139822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 52066ed0-9df4-4311-bc17-208d729b6065 · outbound

This paper cites CIF: Continuous Integrate-And-Fire for End- To-End Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition CIF: Continuous Integrate-And-Fire for End- To-End Speech Recognition,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.995484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b9721592-7df5-4cdc-b957-3bf685542da4 · outbound

This paper cites Hybrid CTC/Attention Architecture for End-to- End Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Hybrid CTC/Attention Architecture for End-to- End Speech Recognition,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.884639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6c29ff97-d4b2-4065-b67f-627e661b22bc · outbound

This paper cites Automatic Channel Selection and Spatial Feature Integration for Multi-Channel Speech Recognition Across Various Array Topologies,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Automatic Channel Selection and Spatial Feature Integration for Multi-Channel Speech Recognition Across Various Array Topologies,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.813692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 761ca2e0-7e83-4c52-b592-398aa3be620f · outbound

This paper cites MMGER: Multi-Modal and Multi-Granularity Generative Error Correction With LLM for Joint Accent and Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition MMGER: Multi-Modal and Multi-Granularity Generative Error Correction With LLM for Joint Accent and Speech Recognition,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.739862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eed92f08-bdad-41fc-814e-1af2332eba4e · outbound

This paper cites An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.641977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8feb82e5-2fbc-4963-b7f9-02cb09d3331e · outbound

This paper cites De- liberation Model Based Two-Pass End-To-End Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition De- liberation Model Based Two-Pass End-To-End Speech Recognition,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.533747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 031b775f-c511-4594-bc82-7994f3b44aab · outbound

This paper cites Component Fusion: Learning Replaceable Language Model Component for End-to-end Speech Recognition System,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Component Fusion: Learning Replaceable Language Model Component for End-to-end Speech Recognition System,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.441300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a476507e-f82a-4215-8903-e676ce97c442 · outbound

This paper cites Cold fusion: Training Seq2seq Models Together with Language Mod- els,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Cold fusion: Training Seq2seq Models Together with Language Mod- els,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.295179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation da3ec169-6db3-4709-9d7f-734bf7416400 · outbound

This paper cites FastCor- rect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition FastCor- rect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.220879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5168ce41-11ea-47d3-89ab-ff8a916abad4 · outbound

This paper cites ASR Error Correction and Domain Adaptation Using Machine Translation,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition ASR Error Correction and Domain Adaptation Using Machine Translation,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:18.077946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4d96d461-0362-42db-b6f5-05d57d67dafd · outbound

This paper cites Softcorrect: Error correction with soft detection for automatic speech recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Softcorrect: Error correction with soft detection for automatic speech recognition,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.942845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e357cc42-edfa-49a4-baea-fdcbe1f4485b · outbound

This paper cites N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.856826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 035cf6a3-6f78-4180-9f4b-66cb54bae7dc · outbound

This paper cites GPT-4 Technical Report.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition GPT-4 Technical Report

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:15.807402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f469721-d505-4b6f-ace7-7a3c9a059e64 · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition PaLM: Scaling Language Modeling with Pathways,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.742764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0dca4184-36bc-4200-8a53-5f305f918e4c · outbound

This paper cites PaLM 2 Technical Report.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition PaLM 2 Technical Report

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:15.899080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6c071da-2225-4215-9c59-561c882f0a98 · outbound

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

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition LLaMA: Open and Efficient Foundation Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:15.977191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0db96c6c-a322-467c-88a8-099ee4753025 · outbound

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

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:16.030640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dda46b1-38d8-4893-85e3-692efbb0daba · outbound

This paper cites HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.653467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1d6b2dab-8d83-401d-bf54-ca0568a4fe9f · outbound

This paper cites Large Language Models are Efficient Learners of Noise-Robust Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Large Language Models are Efficient Learners of Noise-Robust Speech Recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.540480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1fc0987f-9905-4c8d-8af1-6d50a6309a81 · outbound

This paper cites Everyone has an accent,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Everyone has an accent,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.427601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0de2eca8-3174-4582-81b0-7d86768d83f4 · outbound

This paper cites Decoupling and Interacting Multi-Task Learning Network for Joint JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 13 Speech and Accent Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Decoupling and Interacting Multi-Task Learning Network for Joint JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 13 Speech and Accent Recognition,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.275242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3e8f7d8c-d6f7-437e-942e-0b6b84b1417a · outbound

This paper cites Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.162869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bcdfe397-d5fa-4263-ba00-8530d7bed3f7 · outbound

This paper cites A Review of Sparse Expert Models in Deep Learning.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition A Review of Sparse Expert Models in Deep Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:16.494580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff2f5baa-4966-4c59-a6ab-eef86c2a9538 · outbound

This paper cites ST-MoE: Designing Stable and Transferable Sparse Expert Models.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition ST-MoE: Designing Stable and Transferable Sparse Expert Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:16.572247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 711b4b99-1956-47f6-93ed-c4c5bb0d76db · outbound

This paper cites MoEC: Mixture of Expert Clusters,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition MoEC: Mixture of Expert Clusters,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.129930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fed4b699-95b2-4a7d-b537-29eea6986655 · outbound

This paper cites U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:10:19.605346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 635b9630-3af3-4ed5-b557-9fa127260cef · outbound

This paper cites MoLE : Mixture Of Language Experts For Multi-Lingual Automatic Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition MoLE : Mixture Of Language Experts For Multi-Lingual Automatic Speech Recognition,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:17.047492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ef3ff657-56b1-49d8-9eba-488c5b9113cd · outbound

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

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition LoRA: Low-Rank Adaptation of Large Language Models,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:16.937493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 581d6b9d-4afd-4a2f-84b3-e288088a9c76 · outbound

This paper cites When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:16.929883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e4b0da7-1bb9-4306-987c-d951f198565c · outbound

This paper cites Mixture-of-LoRAs: An Efficient Multitask Tuning Method for Large Language Models,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Mixture-of-LoRAs: An Efficient Multitask Tuning Method for Large Language Models,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:16.839584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a96769b4-a15d-493c-a730-e23167e1945e · outbound

This paper cites SiRA: Sparse Mixture of Low Rank Adaptation.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition SiRA: Sparse Mixture of Low Rank Adaptation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:17.154062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 242e7f41-82f2-4b15-89eb-8e51e7646203 · outbound

This paper cites MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:17.252166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 878a8720-cb97-4da4-b0f6-8af1f0705154 · outbound

This paper cites MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:17.346131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ebe83ae-da73-43a6-90e7-274075cc388c · outbound

This paper cites Lo- RAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Lo- RAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:16.691875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d7e8ecb2-49d8-43c6-934b-fe7215e23743 · outbound

This paper cites HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:16.504866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d67fccf2-cf6b-4946-be38-2044fbdb625c · outbound

This paper cites Mixture of LoRA Experts,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Mixture of LoRA Experts,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:16.389863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4be188eb-5aa5-431f-a93e-9809ba2f0f06 · outbound

This paper cites AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:17.661796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19efdf4f-4d33-41d6-9bbe-a9c23ea6a70b · outbound

This paper cites Robust Speech Recognition via Large- Scale Weak Supervision,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Robust Speech Recognition via Large- Scale Weak Supervision,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:16.262877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b2d2732d-cb2f-4498-b07d-0ce0b903b7e9 · outbound

This paper cites Towards Better Decoding and Language Model Integration in Sequence to Sequence Models,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Towards Better Decoding and Language Model Integration in Sequence to Sequence Models,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:16.146108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b87a8417-583d-4bcd-9e80-eeab8fed4057 · outbound

This paper cites Improved Training of End-to-end Attention Models for Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Improved Training of End-to-end Attention Models for Speech Recognition,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.969086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 69437322-8ce7-46b3-9b5b-936bd21d312e · outbound

This paper cites A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.858239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f0aa6ffd-1719-4eae-8436-5798564daa48 · outbound

This paper cites Deliberation Networks: Sequence Generation Beyond One-Pass Decoding,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Deliberation Networks: Sequence Generation Beyond One-Pass Decoding,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.756699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3911c4bf-6c0c-47e2-bd0a-5bc4527e6f06 · outbound

This paper cites Trans- former Based Deliberation for Two-Pass Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Trans- former Based Deliberation for Two-Pass Speech Recognition,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.616465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 95927d9d-0917-48a9-b3ee-b51c61400abd · outbound

This paper cites Scaling Up Deliberation For Multilingual ASR,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Scaling Up Deliberation For Multilingual ASR,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.552519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4f9c4661-177a-4b56-9f78-82338e830ab1 · outbound

This paper cites Language Models are Unsupervised Multitask Learners,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Language Models are Unsupervised Multitask Learners,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.489927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0b0144f8-5bd1-40ed-8abb-484c65e53620 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.380679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ca221bc6-2192-4448-ba6f-3f4ebb26333b · outbound

This paper cites WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.296519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 595ff1bc-65bc-409c-b0eb-8b6cfbf15ca2 · outbound

This paper cites On Online Attention-Based Speech Recognition and Joint Mandarin Character-Pinyin Training,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition On Online Attention-Based Speech Recognition and Joint Mandarin Character-Pinyin Training,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.186574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 52f63b56-3fa0-4423-98f5-391e9a72e511 · outbound

This paper cites A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:15.080242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eba38e9d-8b26-4276-9f5d-cb1f9e7b62ff · outbound

This paper cites On Modular Training of Neural Acoustics-to-Word Model for LVCSR,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition On Modular Training of Neural Acoustics-to-Word Model for LVCSR,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:14.979618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4d1a7878-0447-4063-8fdb-6e17485b6885 · outbound

This paper cites Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:14.919411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7589fa32-d8fe-42ae-81ce-915005b26f4e · outbound

This paper cites Decoupling Recognition and Transcription in Mandarin ASR,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Decoupling Recognition and Transcription in Mandarin ASR,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:14.858119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bdbf4a8d-389a-4def-8d5e-c989e8c0d436 · outbound

This paper cites Cascade RNN- Transducer: Syllable Based Streaming On-Device Mandarin Speech Recognition with a Syllable-To-Character Converter,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Cascade RNN- Transducer: Syllable Based Streaming On-Device Mandarin Speech Recognition with a Syllable-To-Character Converter,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:14.756075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 37860339-e119-4bb9-a1e6-edffa2762d0e · outbound

This paper cites Decoupling Pronunciation and Language for End-to- End Code-Switching Automatic Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Decoupling Pronunciation and Language for End-to- End Code-Switching Automatic Speech Recognition,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:14.610944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0b769ccc-1df9-48bb-b380-c05eb33624c3 · outbound

This paper cites Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:14.523897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aa69cb62-11be-4b97-aac5-c21ae95a592b · outbound

This paper cites On the Properties of Neural Machine Translation: Encoder- Decoder Approaches,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition On the Properties of Neural Machine Translation: Encoder- Decoder Approaches,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:14.417941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3eb28907-dab1-475c-a0b7-ec6d8c438c7c · outbound

This paper cites Common V oice: A Massively-Multilingual Speech Corpus,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Common V oice: A Massively-Multilingual Speech Corpus,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:11:14.241549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d8335a8e-0809-4fd2-9688-f409c35d0485 · outbound

This paper cites The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods,.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:10:19.875855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5a08b818-88d5-4863-90b6-77d17c4fc286 · outbound

This paper cites Qwen2-Audio Technical Report.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition Qwen2-Audio Technical Report

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:19.232070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ef851e9-e40a-4f62-b371-32b5b68955c2 · outbound

This paper cites FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration.

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T18:10:19.311880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers