Paper Citation Record · LEDGER

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty

As of 20 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 1 inbound Pith citation observation for arXiv:2505.16168.

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

pith.paper-citation-record.v1
2505.16168 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:10:51.525953Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:10:48.894279Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T15:10:51.736215Z

Reference resolution

34 of 34 outbound references displayed

verified exact1
verified fuzzy20
unresolved12
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8ee41a53-2c81-45d6-ac91-fcda845a5405 · outbound

This paper cites Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:10:51.764906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ab22dbc8-387b-40ed-bc55-6a339007614c · outbound

This paper cites Invoca- tion No.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Invoca- tion No

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:54.462147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fead3a66-ea5e-47f9-8f00-cc52aff07202 · outbound

This paper cites Uncertain.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Uncertain

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T15:10:54.362733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4e77409c-3e7b-4527-b1c4-e92593824679 · outbound

This paper cites Leveraging a base spoken large lan- guage model, SIMA dynamically determines whether to tran- scribe speech directly or invoke specialized SOTA models.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Leveraging a base spoken large lan- guage model, SIMA dynamically determines whether to tran- scribe speech directly or invoke specialized SOTA models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:54.199507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dd917b33-7b78-4da4-b08c-d0bdb588085a · outbound

This paper cites Multilingual speech recognition with a single end-to-end model,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Multilingual speech recognition with a single end-to-end model,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:54.009014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 635250f3-9361-4ac2-b5a3-57c7ca0430a9 · outbound

This paper cites Cross-lingual language model pre- training,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Cross-lingual language model pre- training,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:53.796090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b2e0ae20-85b0-4690-920e-d63fc598dff2 · outbound

This paper cites Unsupervised cross-lingual representation learning for speech recognition,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Unsupervised cross-lingual representation learning for speech recognition,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:53.618795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e3832067-afd7-49c0-92c7-3e76b1885975 · outbound

This paper cites ML- SUPERB: multilingual speech universal performance bench- mark,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty ML- SUPERB: multilingual speech universal performance bench- mark,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:53.480308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 02823c8f-5fae-4e2d-b62c-9b1e45737132 · outbound

This paper cites Joint unsupervised and supervised training for multilingual ASR,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Joint unsupervised and supervised training for multilingual ASR,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:53.342802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5e2abe37-2c39-4dc3-beeb-c846c861115c · outbound

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

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Robust speech recognition via large-scale weak supervision,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:53.217058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1c9242c5-b1f6-46bd-847b-83a15bcaeb22 · outbound

This paper cites TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representa- tion Learning for Cross-lingual Speech Recognition,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representa- tion Learning for Cross-lingual Speech Recognition,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:53.065505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 95943178-5c95-4853-bba4-e657cfbfea59 · outbound

This paper cites Scaling speech technology to 1, 000+ languages,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Scaling speech technology to 1, 000+ languages,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:49.853701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec704d4a-f35c-42d3-87e9-b3517eb435d4 · outbound

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

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:49.929741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce86b745-3fa2-40b0-a3e4-35bf0274cf1f · outbound

This paper cites SeamlessM4T: Massively Multilingual & Multimodal Machine Translation.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:50.018019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66ccf405-d7e2-471f-8d72-084fd19a614d · outbound

This paper cites SSHR: leveraging self-supervised hierarchical representations for multi- lingual automatic speech recognition,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty SSHR: leveraging self-supervised hierarchical representations for multi- lingual automatic speech recognition,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:52.991999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 68bdb610-ec19-470f-9261-70f881053fd7 · outbound

This paper cites Anatomy of Industrial Scale Multilingual ASR.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Anatomy of Industrial Scale Multilingual ASR

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:50.185658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36ebdfdb-0838-4028-8bc6-0ef4febd8919 · outbound

This paper cites Improving multilingual asr robustness to errors in language in- put,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Improving multilingual asr robustness to errors in language in- put,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:52.877653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 856ff8f9-4ee4-49c0-bd34-27fa7e27a70a · outbound

This paper cites Recurrent neural networks for noise reduction in robust ASR,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Recurrent neural networks for noise reduction in robust ASR,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:52.761316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 146e5fe1-949e-46ea-b40c-19aadd69d117 · outbound

This paper cites MUSAN: A Music, Speech, and Noise Corpus.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty MUSAN: A Music, Speech, and Noise Corpus

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:50.447566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c08fbe-19d3-4182-98ce-6ebe86135c3e · outbound

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

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Wavlm: Large- scale self-supervised pre-training for full stack speech process- ing,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:52.680502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8d23be2d-4729-4a59-a567-b03eb1cd6caa · outbound

This paper cites Noise robust automatic speech recognition: review and analysis,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Noise robust automatic speech recognition: review and analysis,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:52.567397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5b236039-b9a9-4665-92a5-70128b65ecc0 · outbound

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

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty LLaMA: Open and Efficient Foundation Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:50.695453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ec44209-9cef-47d8-b9e8-77cdf91f8b08 · outbound

This paper cites Qwen Technical Report.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Qwen Technical Report

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:50.761636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ce729e8-0eca-4eeb-ae67-420324ba854c · outbound

This paper cites Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:50.833666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1751f849-f5b9-487c-87d7-47f2094d9247 · outbound

This paper cites On decoder-only architecture for speech-to-text and large language model integration,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty On decoder-only architecture for speech-to-text and large language model integration,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:52.474466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e1784789-fecc-41eb-9734-fd1f998b56d5 · outbound

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

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:50.982722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2daee75c-cfe4-43f0-84ab-7385f75fec15 · outbound

This paper cites Wavllm: Towards robust and adaptive speech large language model,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Wavllm: Towards robust and adaptive speech large language model,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:52.358457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a4a2d3d5-0c02-4aee-acd0-7b13ae146a45 · outbound

This paper cites Qwen2-Audio Technical Report.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Qwen2-Audio Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:51.150455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ac4d38-2cca-42b9-8cb3-6e02cc0dd118 · outbound

This paper cites E- chat: Emotion-sensitive spoken dialogue system with large lan- guage models,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty E- chat: Emotion-sensitive spoken dialogue system with large lan- guage models,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:52.242816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3d7c462f-b596-4586-bc49-378cd92b3f4c · outbound

This paper cites MLS: A large-scale multilingual dataset for speech research,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty MLS: A large-scale multilingual dataset for speech research,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:52.114781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0d2688b4-89cc-47f0-afe4-ceb27d073ec8 · outbound

This paper cites V oxpopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty V oxpopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:51.999003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 034e313c-cd43-4117-964d-6e6125ccd671 · outbound

This paper cites FLEURS: few-shot learning evaluation of universal representations of speech,.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty FLEURS: few-shot learning evaluation of universal representations of speech,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:10:51.869947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d27f961e-8767-4e96-9564-58be1f83ed6a · outbound

This paper cites Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:51.482203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 459e50da-1967-46fa-9ada-747cd5cfef81 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:10:51.525953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8ee41a53-2c81-45d6-ac91-fcda845a5405 · inbound