On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition | Paper Citation Record

Observation 86e9cb83-1a16-48d2-b43a-80530049ce7a · outbound

This paper cites an unresolved cited work.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:23:23.316619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation faeefa53-0bd6-42c4-8813-887998166aa4 · outbound

This paper cites On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition

Reference 2

Resolution: malformed identifier; local_arxiv, observed 2026-08-07T13:23:12.459851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0a29b2a5-9b11-495f-9475-3d4c526e337b · outbound

This paper cites an unresolved cited work.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:23:23.096643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0637bb3f-16dd-4bcd-8576-294bf0a5526c · outbound

This paper cites an unresolved cited work.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:23:22.880082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b714dcfa-0dbb-442a-b2e9-21273fa10507 · outbound

This paper cites For example, HuBERT contains three main components: 1) a multi-layer CNN-based feature encoder; 2) an L-layer transformer-based context network with a projection layer; and.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition For example, HuBERT contains three main components: 1) a multi-layer CNN-based feature encoder; 2) an L-layer transformer-based context network with a projection layer; and

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:22.665574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ac4b776f-5ca4-48ce-a08a-50af12f2e4dc · outbound

This paper cites In this paper, we fine-tune the pre-trained HuBERT and WavLM with a CTC decoder.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition In this paper, we fine-tune the pre-trained HuBERT and WavLM with a CTC decoder

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:22.453869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 02080d37-70e0-4b7d-af89-0bd282bb4d9f · outbound

This paper cites !ℒ!%𝑪𝒔𝒀𝒔 BackboneSFM 🔥 a) SAT 🔥Router Requiresdata accumula9on Experts Router 🔥Experts Softmax(𝒂𝟒𝒔)Softmax(𝒂𝟏𝒔)…ℒ12 U?erance of speaker 𝑠 c) Batch-modeℒ!.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition !ℒ!%𝑪𝒔𝒀𝒔 BackboneSFM 🔥 a) SAT 🔥Router Requiresdata accumula9on Experts Router 🔥Experts Softmax(𝒂𝟒𝒔)Softmax(𝒂𝟏𝒔)…ℒ12 U?erance of speaker 𝑠 c) Batch-modeℒ!

Reference 7

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:23:22.344306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation adc1f74a-77a0-4d02-9591-cdc2d4c7c464 · outbound

This paper cites Task Description and Experimental Setup UASpeech [33] is the largest publicly available dysarthric speech dataset containing 16 dysarthric and 13 control speak- ers.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Task Description and Experimental Setup UASpeech [33] is the largest publicly available dysarthric speech dataset containing 16 dysarthric and 13 control speak- ers

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:22.222305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ae55a744-f4da-4723-8bde-84e89e398730 · outbound

This paper cites +” represents score interpolation, while “X →Y.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition +” represents score interpolation, while “X →Y

Reference 9

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:23:21.965019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8d9d3d7c-7014-43dd-b3bc-992b5bd469a7 · outbound

This paper cites 6 & 7 vs.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition 6 & 7 vs

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:21.770473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ef757210-c8aa-4b38-a2f2-05bdcff3c6e1 · outbound

This paper cites while operating approximately 7 times faster in terms of RTF (Sys.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition while operating approximately 7 times faster in terms of RTF (Sys

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:21.565645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b761e83f-5beb-4105-bc29-6ea560f3158c · outbound

This paper cites Know. ”) integration and KL loss, as well as on-the-fly MoE-based speaker adaptation with and with- out attentive pooling (“Atten. Pool.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Know. ”) integration and KL loss, as well as on-the-fly MoE-based speaker adaptation with and with- out attentive pooling (“Atten. Pool

Reference 12

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:23:12.173492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 64085c14-3261-43ad-bf5b-98d609ed995c · outbound

This paper cites Feature- driven routing networks are designed to produce homogeneous SD routing parameters on the fly, thereby facilitating zero-shot and real-time speaker adaptation.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Feature- driven routing networks are designed to produce homogeneous SD routing parameters on the fly, thereby facilitating zero-shot and real-time speaker adaptation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:21.356654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f3a129e3-69fd-4d6f-ac2f-8e11afa3bedd · outbound

This paper cites 14200220, 14200021, 14200324, TRS T45-407/19N, Innova- tion Technology Fund grant No.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition 14200220, 14200021, 14200324, TRS T45-407/19N, Innova- tion Technology Fund grant No

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:21.150921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 826a1e35-1032-4f17-a8b5-5626e978a53a · outbound

This paper cites Model adaptation and adaptive training for the recognition of dysarthric speech,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Model adaptation and adaptive training for the recognition of dysarthric speech,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:21.011328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation abf6e160-e48a-4f47-9d52-0d638510ccca · outbound

This paper cites Deep learning of articulatory-based representa- tions and applications for improving dysarthric speech recogni- tion,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Deep learning of articulatory-based representa- tions and applications for improving dysarthric speech recogni- tion,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:20.823706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 666453ac-c542-4d46-8b49-e0ec40fa50e1 · outbound

This paper cites Recent Progress in the CUHK Dysarthric Speech Recognition System,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Recent Progress in the CUHK Dysarthric Speech Recognition System,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:20.693724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 09442f9d-ea9e-4aee-922f-21901eaa4a2c · outbound

This paper cites Speaker adaptation using spectro-temporal deep features for dysarthric and elderly speech recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Speaker adaptation using spectro-temporal deep features for dysarthric and elderly speech recognition,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:20.533604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c1485fa8-fe04-465b-afdb-b2d095240d62 · outbound

This paper cites Exploring Self-supervised Pre-trained ASR Mod- els For Dysarthric and Elderly Speech Recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Exploring Self-supervised Pre-trained ASR Mod- els For Dysarthric and Elderly Speech Recognition,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:20.390024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 598f8b99-935c-421f-b063-1fb1b959ba7d · outbound

This paper cites Acoustic Modelling From Raw Source and Filter Components for Dysarthric Speech Recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Acoustic Modelling From Raw Source and Filter Components for Dysarthric Speech Recognition,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:20.273774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c6baa42d-9283-4ab7-bae7-5d39f1bad846 · outbound

This paper cites Exploiting Cross-Domain And Cross-Lingual Ul- trasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Exploiting Cross-Domain And Cross-Lingual Ul- trasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:20.144647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bb94f6e1-6e5e-4f03-b10f-d54c493dd535 · outbound

This paper cites Exploiting Cross Domain Acoustic-to- articulatory Inverted Features for Disordered Speech Recogni- tion,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Exploiting Cross Domain Acoustic-to- articulatory Inverted Features for Disordered Speech Recogni- tion,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:20.037160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 99668a7e-0a8e-4dfe-a6c6-9b581b4e0ff7 · outbound

This paper cites Self-Supervised ASR Models and Features for Dysarthric and Elderly Speech Recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Self-Supervised ASR Models and Features for Dysarthric and Elderly Speech Recognition,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:19.780422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 92c04527-44f0-4ca2-ac89-086e73c21f74 · outbound

This paper cites Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Structured Speaker-Deficiency Adaptation of Foundation Models for Dysarthric and Elderly Speech Recognition

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:02.500326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee00a521-103c-468f-ab54-d62c7bbe50fb · outbound

This paper cites Temporal characteristics of the speech of nor- mal elderly adults,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Temporal characteristics of the speech of nor- mal elderly adults,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:19.567794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 936bd237-51dc-4721-bdfb-dab23da418c8 · outbound

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

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition wav2vec 2.0: A framework for self-supervised learning of speech representations,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:19.366454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6d9c71f1-1fb8-4fe9-be25-301f6dcfa5bb · outbound

This paper cites Wavlm: Large-scale self-supervised pre-training for full stack speech processing,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Wavlm: Large-scale self-supervised pre-training for full stack speech processing,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:19.174939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation aac3e7a3-ec03-432c-bb83-4a6d7ae2172e · outbound

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

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Hubert: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:18.880262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 707c04cf-b1e7-4622-9330-debdcedf17cd · outbound

This paper cites Speaker adaptation for Wav2vec2 based dysarthric ASR,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Speaker adaptation for Wav2vec2 based dysarthric ASR,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:18.592971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7c5dfd4a-7862-4c02-8c64-725d4a07ca0e · outbound

This paper cites Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recogni- tion,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recogni- tion,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:18.345448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8ac43a61-6993-4d17-89e9-7b91ac896fdf · outbound

This paper cites Efficient adapter transfer of self-supervised speech models for automatic speech recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Efficient adapter transfer of self-supervised speech models for automatic speech recognition,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:18.100852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7b2d9680-da0a-4999-b6e4-8c17f8680a93 · outbound

This paper cites Exploring Efficient-Tuning Methods in Self- Supervised Speech Models,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Exploring Efficient-Tuning Methods in Self- Supervised Speech Models,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:17.837816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 082da81a-8c80-4dd9-8f69-9972652e4ba2 · outbound

This paper cites Efficient Domain Adaptation for Speech Foundation Models,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Efficient Domain Adaptation for Speech Foundation Models,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:17.520010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d6b96be0-9068-4046-8137-175510c05587 · outbound

This paper cites Chapter: Exploiting Convolutional Neural Net- work Adapters for Self-Supervised Speech Models,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Chapter: Exploiting Convolutional Neural Net- work Adapters for Self-Supervised Speech Models,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:17.271284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 60e1cd43-ac2b-4a77-9066-0474c772fd90 · outbound

This paper cites Adaptive mixtures of local experts,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Adaptive mixtures of local experts,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:17.082978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a8ca9c9c-6c01-44c1-bb55-73ffd8645b96 · outbound

This paper cites Hierarchical mixtures of experts and the EM algorithm,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Hierarchical mixtures of experts and the EM algorithm,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:16.803367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation da0b08c3-17ed-4d48-879b-ee6f1f77e721 · outbound

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

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:04.605867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3e8cc71-dbc4-49b0-9375-192a692f859e · outbound

This paper cites Mixtral of Experts.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Mixtral of Experts

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:04.737947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d78c9a1-df5b-40e7-9b27-df6f1a1320ca · outbound

This paper cites DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:04.927651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b30712b0-0274-4053-aade-9b5fe9d872b2 · outbound

This paper cites Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:06.618315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669f59f5-79c2-41a4-b28d-d75d0665dee1 · outbound

This paper cites SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:16.569680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cd4126f6-eba5-4cc1-83a6-dbf81b3c7cc7 · outbound

This paper cites Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:16.332982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d8f25fee-13ab-4618-8222-5787cdee0fe5 · outbound

This paper cites BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:16.101131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6b956d9d-1a34-401c-a5c7-85b6c20ab2f5 · outbound

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

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition MoLE : Mixture Of Language Experts For Multi- Lingual Automatic Speech Recognition,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:15.904723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7518881b-d615-421d-b28d-c59eee8143b7 · outbound

This paper cites Aphasic Speech Recognition Using a Mixture of Speech Intelligibility Experts,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Aphasic Speech Recognition Using a Mixture of Speech Intelligibility Experts,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:15.649210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 33ff3695-4c1d-4df0-9282-224a1b564567 · outbound

This paper cites SAML: Speaker Adaptive Mixture of LoRA Ex- perts for End-to-End ASR,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition SAML: Speaker Adaptive Mixture of LoRA Ex- perts for End-to-End ASR,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:15.369906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3089c1e5-89b1-4d8a-ae36-e63cdb47a2a4 · outbound

This paper cites Dysarthric speech database for universal access research,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Dysarthric speech database for universal access research,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:15.148513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 96c8a441-d6ec-4103-8c01-30f71a03f0f7 · outbound

This paper cites Use of Speech Impairment Severity for Dysarthric Speech Recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Use of Speech Impairment Severity for Dysarthric Speech Recognition,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:14.984656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 364d7455-bf97-4e12-9ff2-e49849bf8efe · outbound

This paper cites Attentive statistics pooling for deep speaker em- bedding,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Attentive statistics pooling for deep speaker em- bedding,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:14.774551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 67c4e633-b631-4e9f-89f0-17c37d276cb2 · outbound

This paper cites Investigation of Data Augmentation Techniques for Disordered Speech Recognition.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Investigation of Data Augmentation Techniques for Disordered Speech Recognition

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:14.564790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c5f8561a-3bd7-4509-a179-a4443e00c0a6 · outbound

This paper cites Some statistical issues in the comparison of speech recognition algorithms,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Some statistical issues in the comparison of speech recognition algorithms,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:14.284006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ec8c87d1-7330-4adb-b81c-f5a59d3bd80b · outbound

This paper cites Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Investigating Self-supervised Pretraining Frameworks for Pathological Speech Recognition,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:13.953364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 82cb5a7b-c210-42dc-85b6-85cd3cfc7f1b · outbound

This paper cites Cross-lingual Self-Supervised Speech Rep- resentations for Improved Dysarthric Speech Recognition,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Cross-lingual Self-Supervised Speech Rep- resentations for Improved Dysarthric Speech Recognition,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:13.596899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 77c45d1a-8f88-42fd-8236-e1231a7d95e6 · outbound

This paper cites DuTa-VC: A Duration-aware Typical-to-atypical V oice Conversion Approach with Diffusion Probabilistic Model,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition DuTa-VC: A Duration-aware Typical-to-atypical V oice Conversion Approach with Diffusion Probabilistic Model,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:13.293613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 47a2dcca-6c42-48c4-a3b2-fd419009e28d · outbound

This paper cites Enhancing Pre-Trained ASR System Fine-Tuning for Dysarthric Speech Recognition Using Adversar- ial Data Augmentation,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Enhancing Pre-Trained ASR System Fine-Tuning for Dysarthric Speech Recognition Using Adversar- ial Data Augmentation,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:12.980593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fc26ce48-21db-4961-b803-33227f74efda · outbound

This paper cites Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T13:23:11.614516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aabcfa32-cb43-4404-b023-ba6036a7a2bf · outbound

This paper cites Improving Acoustic Models in TORGO Dysarthric Speech Database,.

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition Improving Acoustic Models in TORGO Dysarthric Speech Database,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:23:12.729237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers