Paper Citation Record · LEDGER

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition

As of 16 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2412.17507.

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

pith.paper-citation-record.v1
2412.17507 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T05:31:45.902125Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

42 of 42 outbound references displayed

verified exact1
verified fuzzy35
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 91858430-01ae-44bf-b2d9-5ae3ec0d0d22 · outbound

This paper cites Attention is all you need,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Attention is all you need,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.506628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1f849a45-c831-45ba-bdb9-07242e5e4ccc · outbound

This paper cites Recent advances in end-to-end automatic speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Recent advances in end-to-end automatic speech recognition,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.492646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4cca7ba5-2d3f-4584-95ad-d41652265d42 · outbound

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

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition End-to- end speech recognition: A survey,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.476625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b16e0c43-5cb9-46f4-8ee5-999aa01d80b4 · outbound

This paper cites Bigssl: Exploring the frontier of large-scale semi-supervised learning for automatic speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Bigssl: Exploring the frontier of large-scale semi-supervised learning for automatic speech recognition,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.464356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 92785e70-24ab-477d-a5cb-9ccd452425b5 · outbound

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

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Wavlm: Large- scale self-supervised pre-training for full stack speech processing,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.449827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d190ecf2-f186-45b7-b1ea-eaaad5dfd948 · outbound

This paper cites Pushing the limits of semi- supervised learning for automatic speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Pushing the limits of semi- supervised learning for automatic speech recognition,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.437037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7451cc52-3353-466f-84d0-d76ed300e440 · outbound

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

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Robust speech recogni- tion via large-scale weak supervision,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.422142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6bcfa17e-9736-4f08-ae87-0c2c8ec0d0a4 · outbound

This paper cites Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:45.770718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18e5fd35-1719-4844-9b4b-176939978b38 · outbound

This paper cites On Efficient Training of Large-Scale Deep Learning Models: A Literature Review.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition On Efficient Training of Large-Scale Deep Learning Models: A Literature Review

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:45.774570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf954ae4-0aae-4d7f-98a6-b33c75da68b9 · outbound

This paper cites Net2net: Acceler- ating learning via knowledge transfer,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Net2net: Acceler- ating learning via knowledge transfer,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.408936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b8bdb601-bccf-4a04-aca7-326d6d2d4a46 · outbound

This paper cites Data efficient neural scaling law via model reusing,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Data efficient neural scaling law via model reusing,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.397473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 68a09b74-fcdb-4790-80ef-7fbf0f5b7ba5 · outbound

This paper cites Efficient large scale language modeling with mixtures of experts,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Efficient large scale language modeling with mixtures of experts,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.384490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d236518d-72fc-4d6b-aa6b-78ade80b0a57 · outbound

This paper cites Mixtral of Experts.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Mixtral of Experts

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:45.789552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f7f3164-72ae-4164-a6c5-9a6a8f267683 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:45.793319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ad9ae1f-4aec-47c2-9ea5-b24117f19c03 · outbound

This paper cites Sparse upcycling: Training mixture-of-experts from dense checkpoints,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Sparse upcycling: Training mixture-of-experts from dense checkpoints,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.373278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e68c2cae-07a4-4cf8-b04a-7c9dc1072931 · outbound

This paper cites MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:31:45.977205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 22e31cbf-aa8b-4832-a110-8c11437741b9 · outbound

This paper cites Outra- geously large neural networks: The sparsely-gated mixture-of-experts layer,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Outra- geously large neural networks: The sparsely-gated mixture-of-experts layer,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.359977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dfe9aad1-2088-4426-a315-3f3701bb93d3 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.345079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0433a52d-9974-45d8-a935-241f8e0a4726 · outbound

This paper cites Speechmoe: Scaling to large acoustic models with dynamic routing mixture of experts,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Speechmoe: Scaling to large acoustic models with dynamic routing mixture of experts,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.331773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 71bba485-a8ab-4cc2-ad44-14b62efe5a74 · outbound

This paper cites Speechmoe2: Mixture-of-experts model with improved routing,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Speechmoe2: Mixture-of-experts model with improved routing,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.318884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation df524522-8643-47a0-9bae-bc3a6e35cb4d · outbound

This paper cites 3m: Multi-loss, multi-path and multi-level neural networks for speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition 3m: Multi-loss, multi-path and multi-level neural networks for speech recognition,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.292841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9f9ce6dc-068f-4ee3-afe1-18ac1e63c979 · outbound

This paper cites Language-routing mix- ture of experts for multilingual and code-switching speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Language-routing mix- ture of experts for multilingual and code-switching speech recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.279470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7057ea70-e4d2-460b-9d6e-5d4da7d31812 · outbound

This paper cites Ba-moe: Boundary-aware mixture-of-experts adapter for code-switching speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Ba-moe: Boundary-aware mixture-of-experts adapter for code-switching speech recognition,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.266505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1ddc3055-b65d-4c0a-83b6-962f461a80cd · outbound

This paper cites Mole: Mixture of language experts for multi-lingual automatic speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Mole: Mixture of language experts for multi-lingual automatic speech recognition,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.253806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 51f16ebd-3beb-4fb6-bee5-98916dadd991 · outbound

This paper cites Mixture-of-expert conformer for streaming multilingual asr,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Mixture-of-expert conformer for streaming multilingual asr,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.239057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8894a8e9-e7f0-4f8e-9663-1ccc5aab77ab · outbound

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

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:45.841860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7bfca95-001c-472c-9a83-8b521bc67ed7 · outbound

This paper cites Conformer: Convolution-augmented transformer for speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Conformer: Convolution-augmented transformer for speech recognition,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.225749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation facb98b8-aab9-4b2f-ad77-5059ade415ae · outbound

This paper cites Massively multilingual asr: A lifelong learning solution,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Massively multilingual asr: A lifelong learning solution,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.212790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aea8e3b8-9c32-4e58-a10a-53fc946bda22 · outbound

This paper cites Incremental learning for end-to-end automatic speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Incremental learning for end-to-end automatic speech recognition,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.199163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2af63dbc-1672-4872-aa08-003ca776277b · outbound

This paper cites A comparison of parameter-efficient asr domain adaptation methods for universal speech and language models,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition A comparison of parameter-efficient asr domain adaptation methods for universal speech and language models,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.186582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fa956995-f1cf-4192-b21c-d8ac917ac5b9 · outbound

This paper cites Lora: Low-rank adaptation of large language models,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Lora: Low-rank adaptation of large language models,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.175266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 04997137-ffdb-40c0-b13c-d19b58afac2f · outbound

This paper cites Sparsely shared lora on whisper for child speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Sparsely shared lora on whisper for child speech recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.160691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b9738662-3ee6-45d4-b668-d835e68a7166 · outbound

This paper cites Residual adapters for parameter-efficient asr adaptation to atypical and accented speech,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Residual adapters for parameter-efficient asr adaptation to atypical and accented speech,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.148401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8244306a-1a7d-416a-a308-dbb1625557fe · outbound

This paper cites Exploiting adapters for cross-lingual low-resource speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Exploiting adapters for cross-lingual low-resource speech recognition,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.134720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation acfff059-c171-4953-841d-c1130836428d · outbound

This paper cites Funasr: A fundamental end-to-end speech recognition toolkit,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Funasr: A fundamental end-to-end speech recognition toolkit,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.121515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 62d2b0f0-26de-4e4a-8736-db5e212d91c2 · outbound

This paper cites Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to- end speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to- end speech recognition,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.107474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 757865e8-760a-464c-bca9-03f4113f0029 · outbound

This paper cites LLaMA Pro: Progressive LLaMA with Block Expansion.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition LLaMA Pro: Progressive LLaMA with Block Expansion

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T05:31:45.884693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3405737-ff8a-477c-8968-4907267130bd · outbound

This paper cites Smartfrz: An efficient train- ing framework using attention-based layer freezing,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Smartfrz: An efficient train- ing framework using attention-based layer freezing,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.093447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5b638b6e-9ab0-4595-bb64-6961b0ef84cc · outbound

This paper cites Wenetspeech: A 10000+ hours multi-domain mandarin corpus for speech recognition,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Wenetspeech: A 10000+ hours multi-domain mandarin corpus for speech recognition,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.081135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 61eaed8a-96b9-4b27-bb7d-9cc5ebb98b23 · outbound

This paper cites Aishell-4: An open source dataset for speech enhancement, separation, recognition and speaker diarization in conference scenario,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Aishell-4: An open source dataset for speech enhancement, separation, recognition and speaker diarization in conference scenario,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.068826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9691e893-35fc-4902-abaa-50373cdab966 · outbound

This paper cites Gigaspeech: An evolving, multi-domain asr corpus with 10,000 hours of transcribed audio,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Gigaspeech: An evolving, multi-domain asr corpus with 10,000 hours of transcribed audio,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.055397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fd43b5ba-6aaa-4517-9bca-f4a668e883be · outbound

This paper cites Connection- ist temporal classification: Labelling unsegmented sequence data with recurrent neural networks,.

UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition Connection- ist temporal classification: Labelling unsegmented sequence data with recurrent neural networks,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:31:46.042820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

No inbound Pith citation observations are available.