Paper Citation Record · LEDGER

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining

As of 8 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2505.21527.

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

pith.paper-citation-record.v1
2505.21527 v2

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:40:58.184272Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:40:55.130431Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T14:40:58.467883Z

Reference resolution

39 of 39 outbound references displayed

verified exact2
verified fuzzy28
unresolved8
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 65d84a78-a98e-4a4b-8675-03b7925b264d · outbound

This paper cites VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:40:58.530962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation de4a9de8-727f-4be7-9c6f-5a146bfde3bf · outbound

This paper cites It adopts the model architecture of wav2vec 2.0 [13], comprising a CNN feature extractor to convert waveform into a local feature, and a trans- former as the context network.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining It adopts the model architecture of wav2vec 2.0 [13], comprising a CNN feature extractor to convert waveform into a local feature, and a trans- former as the context network

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:05.641541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5dbe9ec4-d12b-401b-beeb-e6b904a1eed6 · outbound

This paper cites The design of VietASR focuses on two key aspects: • Adapting HuBERT-style multi-iteration pre-training to Zip- former encoder for better efficiency and practicality.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining The design of VietASR focuses on two key aspects: • Adapting HuBERT-style multi-iteration pre-training to Zip- former encoder for better efficiency and practicality

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:05.441209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9f97d229-19dc-4b6d-8446-ca676a4dd1c6 · outbound

This paper cites Experimental Setups DatasetWe collect approximately 70,000 hours of unlabeled audio from YouTube and apply FunASR V AD [29] for auto- matic segmentation.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Experimental Setups DatasetWe collect approximately 70,000 hours of unlabeled audio from YouTube and apply FunASR V AD [29] for auto- matic segmentation

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:41:05.219853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 12a84b64-3423-4ba8-9df2-21edc5846b27 · outbound

This paper cites an unresolved cited work.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:41:05.029933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 24d531c7-ee05-4133-b175-ae598a2439d6 · outbound

This paper cites 62206171 and No.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining 62206171 and No

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:04.912706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation db0fa5a5-0772-41f2-8273-e38ff4257fec · outbound

This paper cites Con- nectionist temporal classification: labelling unsegmented se- quence data with recurrent neural networks,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Con- nectionist temporal classification: labelling unsegmented se- quence data with recurrent neural networks,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:40:55.658199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7210083-2055-4e58-8d4d-7c8dbe2a9246 · outbound

This paper cites Speech recognition with deep recurrent neural networks,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Speech recognition with deep recurrent neural networks,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:04.839881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 46c7cb3a-cb57-4af3-bf3f-45df80f2affb · outbound

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

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Recent advances in end-to-end automatic speech recognition,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:04.686802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8a6f43b9-dfd4-460c-b9d2-12670fcff2cc · outbound

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

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Robust speech recognition via large-scale weak supervision,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:04.497093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7e660ff5-0a7d-4bfe-af5a-21dc603fa87a · outbound

This paper cites Less is More: Accurate Speech Recognition & Translation without Web-Scale Data.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Less is More: Accurate Speech Recognition & Translation without Web-Scale Data

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:40:56.020123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f183e45-2c90-4043-b9b8-0574e6dcc66e · outbound

This paper cites Anatomy of Industrial Scale Multilingual ASR.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Anatomy of Industrial Scale Multilingual ASR

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:40:56.096569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a1c20a4-59bd-408a-b4fc-cb394ee91ef2 · outbound

This paper cites XLS-R: Self-supervised cross-lingual speech representation learning at scale,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining XLS-R: Self-supervised cross-lingual speech representation learning at scale,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:04.326056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5adc19bc-4bbb-4c92-a428-b302d83d4cb9 · outbound

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

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:40:56.281578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf33fbb6-29df-4d59-af0c-fe2aa7e6f159 · outbound

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

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Scaling speech technology to 1,000+ languages,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:04.155444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9d714c57-19f2-4fc1-b1f0-5d52f075dc74 · outbound

This paper cites GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:40:56.424529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cdb175a-606e-4f95-97ee-14b6c4999a41 · outbound

This paper cites Zipformer: A faster and better encoder for automatic speech recognition,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Zipformer: A faster and better encoder for automatic speech recognition,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:03.960241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f24ae292-a21b-4712-b1c4-823fff75c31d · outbound

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

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining HuBERT: Self- supervised speech representation learning by masked prediction of hidden units,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:03.779728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bb4dee4f-b0de-49fb-b540-82fc9a03338b · outbound

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

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining wav2vec 2.0: A framework for self-supervised learning of speech representa- tions,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:40:56.682166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c77a193-e8f3-4991-bd30-1b4ee2e889cb · outbound

This paper cites Supervision-guided codebooks for masked prediction in speech pre-training,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Supervision-guided codebooks for masked prediction in speech pre-training,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:03.566036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b1889d01-5a99-4ba5-8a77-8513df587842 · outbound

This paper cites Pushing the limits of unsu- pervised unit discovery for SSL speech representation,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Pushing the limits of unsu- pervised unit discovery for SSL speech representation,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:03.381198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cd1d3ff6-1d00-49e3-933d-9b7a6d7ea321 · outbound

This paper cites Speech pre-training with acoustic piece,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Speech pre-training with acoustic piece,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:03.136150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2d57d349-ba99-4a16-8e7e-dd06cb8d2102 · outbound

This paper cites Reducing barriers to self- supervised learning: HuBERT pre-training with academic com- pute,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Reducing barriers to self- supervised learning: HuBERT pre-training with academic com- pute,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:02.934554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 94c5224f-f293-4030-af5c-3a042eed7213 · outbound

This paper cites ASBERT: ASR-specific self-supervised learning with self-training,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining ASBERT: ASR-specific self-supervised learning with self-training,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:02.650999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e735ec1a-48bc-4e48-a036-95e1a21efbb3 · outbound

This paper cites Biased self-supervised learn- ing for ASR,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Biased self-supervised learn- ing for ASR,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:02.340163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 658cafe9-371f-4274-aae1-8e9ca793f995 · outbound

This paper cites CTCBERT: Advancing hidden-unit BERT with CTC objectives,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining CTCBERT: Advancing hidden-unit BERT with CTC objectives,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:02.014116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 185faf4b-8ad9-4b2e-8450-615775fb5044 · outbound

This paper cites MelHuBERT: A simplified hubert on mel spectrograms,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining MelHuBERT: A simplified hubert on mel spectrograms,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:01.731030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8b294522-c8e7-47d9-a11a-fb2f6d81e137 · outbound

This paper cites Fast-HuBERT: an efficient train- ing framework for self-supervised speech representation learn- ing,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Fast-HuBERT: an efficient train- ing framework for self-supervised speech representation learn- ing,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:01.310181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2ff276ab-f86e-4d6c-8636-b72a67c6d58f · outbound

This paper cites k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:40:58.375212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 60473076-953f-4088-af91-15110098a2d7 · outbound

This paper cites Attention is all you need,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Attention is all you need,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:00.911254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2866d0b3-6706-4cf5-b9be-3d13cf691ab2 · outbound

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

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Conformer: Convolution- augmented transformer for speech recognition,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:00.564659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bfb2ddae-a7b0-40a6-8b5d-1d7790a0916a · outbound

This paper cites RNN-Transducer with state- less prediction network,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining RNN-Transducer with state- less prediction network,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:41:00.246108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6df46cdf-ec7c-4aa0-9c51-f867afb16a66 · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Sequence Transduction with Recurrent Neural Networks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:40:57.720390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17bfa531-9525-4c70-9cab-eab692c8a0b6 · outbound

This paper cites Pruned RNN-T for fast, memory-efficient ASR training,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Pruned RNN-T for fast, memory-efficient ASR training,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:40:59.975823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9d6a4ccd-2d8c-43a2-9cfa-42e0e0700a4d · outbound

This paper cites FunASR: A fundamental End-to- End speech recognition toolkit,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining FunASR: A fundamental End-to- End speech recognition toolkit,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:40:59.717498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3b60f1d2-e23b-4994-a296-d4af54a2c6c4 · outbound

This paper cites Common V oice: A massively-multilingual speech corpus,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Common V oice: A massively-multilingual speech corpus,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:40:59.486033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 345f2766-ae97-4c6b-9007-eaf692de65a8 · outbound

This paper cites FLEURS: Few-shot learn- ing evaluation of universal representations of speech,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining FLEURS: Few-shot learn- ing evaluation of universal representations of speech,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:40:59.200412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fac63337-1850-4832-86db-c98048697c26 · outbound

This paper cites Neural machine transla- tion of rare words with subword units,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Neural machine transla- tion of rare words with subword units,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:40:58.936309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0ee7bf36-b861-4bc0-8496-1a9ee5d44281 · outbound

This paper cites Fast and parallel decoding for transducer,.

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining Fast and parallel decoding for transducer,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:40:58.620250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 65d84a78-a98e-4a4b-8675-03b7925b264d · inbound