Paper Citation Record · LEDGER

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data

As of 20 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2506.16251.

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

pith.paper-citation-record.v1
2506.16251 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:50:01.081135Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:49:57.895080Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T23:50:01.121583Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy33
unresolved4
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 59ca3403-6620-4442-bd77-88a377d90e41 · outbound

This paper cites The widely used datasets for ST re- search are CoV oST [7] and MUST-C [8], which are built on top of Mozilla common voice [9] and TED-talks respectively.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data The widely used datasets for ST re- search are CoV oST [7] and MUST-C [8], which are built on top of Mozilla common voice [9] and TED-talks respectively

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.510525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 955449d6-9fc4-49f0-9470-d5a44965a8ff · outbound

This paper cites Details are discussed in Section 2.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Details are discussed in Section 2

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.499547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 369761aa-cdca-4b0f-ab1a-72ff9691d6aa · outbound

This paper cites an unresolved cited work.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:50:01.490022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 843a3075-4d83-4398-96a8-a19216491c35 · outbound

This paper cites The data and code are available at: https://github.com/ aishwaryapothula/Shrutilipi-Anuvaad.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data The data and code are available at: https://github.com/ aishwaryapothula/Shrutilipi-Anuvaad

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.480661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2f91e77d-577d-4024-8772-e556175274b0 · outbound

This paper cites End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data

Reference 5

Resolution: malformed identifier; local_arxiv, observed 2026-08-06T23:50:01.127714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1a49f326-54e3-4122-b7ea-92e033d83445 · outbound

This paper cites an unresolved cited work.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:50:01.471830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c0f76e55-3da6-4e99-a91c-e5a9403de2c8 · outbound

This paper cites The training data are aug- mented with speed perturbations using factors of 0.9, 1, and 1.1.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data The training data are aug- mented with speed perturbations using factors of 0.9, 1, and 1.1

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.462792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 543f818f-07d1-44f0-a23b-5a8e91b34e14 · outbound

This paper cites Linguistics, Artificial Intelligence and Language and Speech Technologies: from Research to Applications.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Linguistics, Artificial Intelligence and Language and Speech Technologies: from Research to Applications

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.412851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0dce3a64-7092-4b42-949d-74a6d2a5b657 · outbound

This paper cites S5} independently.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data S5} independently

Reference 9

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T23:50:01.442211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8023bbf6-608d-4190-b10e-5bec1033c053 · outbound

This paper cites Table 4: p values for the statistical significance test for ST mod- els trained on S1 performing better than models trained on S5 in terms of BLEU scores.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Table 4: p values for the statistical significance test for ST mod- els trained on S1 performing better than models trained on S5 in terms of BLEU scores

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.452816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 91859106-fe97-48a4-85ca-671d08859e37 · outbound

This paper cites To this extent, we built our ST corpus,Shrutilipi-anuvaad, based on the multilingual Shrutilipi corpus by automatically mining parallel texts using the SONAR sentence encoder.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data To this extent, we built our ST corpus,Shrutilipi-anuvaad, based on the multilingual Shrutilipi corpus by automatically mining parallel texts using the SONAR sentence encoder

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.432158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a18999c9-2050-41df-bcc6-5b0ce46744fa · outbound

This paper cites Additionally, our pre-trained models are also de- rived from the same domain, which may influence performance.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Additionally, our pre-trained models are also de- rived from the same domain, which may influence performance

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.422908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a2b6c8f2-9d10-47de-9128-2561c1f86365 · outbound

This paper cites Findings of the IWSLT 2023 Evaluation Campaign,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Findings of the IWSLT 2023 Evaluation Campaign,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.402356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1412727e-83af-4ad7-9b76-60a3b703e6e7 · outbound

This paper cites Findings of the IWSLT 2024 Evaluation Campaign,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Findings of the IWSLT 2024 Evaluation Campaign,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.391529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation aaf5b3bb-c9c5-4a74-97f0-004b2f9a9b14 · outbound

This paper cites Analyzing ASR Pre- training for Low-Resource Speech-to-Text Translation,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Analyzing ASR Pre- training for Low-Resource Speech-to-Text Translation,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.380807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4fd6ec44-a00e-4c74-b805-c12e511ef519 · outbound

This paper cites Strategies for Improving Low Resource Speech to Text Transla- tion Relying on Pre-trained ASR Models,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Strategies for Improving Low Resource Speech to Text Transla- tion Relying on Pre-trained ASR Models,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.371700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2e9f0742-79de-4a92-99ff-372b44c97fa9 · outbound

This paper cites SeamlessM4T: Massively Multilingual & Multi- modal Machine Translation,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data SeamlessM4T: Massively Multilingual & Multi- modal Machine Translation,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.362221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e7308f20-8bf4-45a2-ab1b-9046d40500ce · outbound

This paper cites UnitY: Two- pass direct speech-to-speech translation with discrete units,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data UnitY: Two- pass direct speech-to-speech translation with discrete units,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.352024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2c218d3e-d3e3-43d3-b9bf-1bed33bcba64 · outbound

This paper cites Covost 2 and massively multilingual speech translation,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Covost 2 and massively multilingual speech translation,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.341687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 27a6b54d-d5f8-48ab-ae43-c0ad8a98993f · outbound

This paper cites MuST-C: a Multilingual Speech Translation Corpus,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data MuST-C: a Multilingual Speech Translation Corpus,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.330970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9e736290-5ed6-49dd-a73d-340b5202aca2 · outbound

This paper cites Com- mon voice: A massively-multilingual speech corpus,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Com- mon voice: A massively-multilingual speech corpus,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.319742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c670375c-d748-45ab-84c7-6494bb9ddfff · outbound

This paper cites Speech resources in the Tamasheq language,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Speech resources in the Tamasheq language,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.309629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1b902abb-b0df-4e2b-8cf7-c943df6ca597 · outbound

This paper cites Sim- inchik: A speech corpus for preservation of southern Quechua,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Sim- inchik: A speech corpus for preservation of southern Quechua,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.298927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dd58dc81-4843-430f-99c8-99cd174d7747 · outbound

This paper cites SpeechMatrix: A large-scale mined corpus of multilingual speech-to-speech trans- lations,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data SpeechMatrix: A large-scale mined corpus of multilingual speech-to-speech trans- lations,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.289048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 65c20709-0a2a-4b29-a10a-3ac333ad08aa · outbound

This paper cites Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.278453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3270c131-a266-43ab-8eba-0a5d5acd6e5b · outbound

This paper cites Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Sys- tems for Low-Resource Languages,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Sys- tems for Low-Resource Languages,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.267316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fc82ec79-937b-4bec-a905-087372800156 · outbound

This paper cites SONAR: Sentence- Level Multimodal and Language-Agnostic Representations,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data SONAR: Sentence- Level Multimodal and Language-Agnostic Representations,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.257167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 435ec8b3-117a-4188-932a-9b7618e305c7 · outbound

This paper cites Multimodal and multilingual embeddings for large-scale speech mining,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Multimodal and multilingual embeddings for large-scale speech mining,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.246460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 01a7da94-5776-4c85-bbd6-cc62dedd4c3e · outbound

This paper cites CCMatrix: Mining billions of high-quality parallel sen- tences on the web,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data CCMatrix: Mining billions of high-quality parallel sen- tences on the web,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.235755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 25e535a3-423a-43ec-b52b-fe0178794871 · outbound

This paper cites Findings of the WMT 2023 shared task on parallel data curation,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Findings of the WMT 2023 shared task on parallel data curation,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.225032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 67e1bfde-f2df-428f-b548-2f88d136a77f · outbound

This paper cites Low-resource corpus filtering using multilingual sentence em- beddings,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Low-resource corpus filtering using multilingual sentence em- beddings,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.214490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c5b7f724-ce12-4768-b4f3-52ddf75fe019 · outbound

This paper cites Indic-TEDST: Datasets and baselines for low-resource speech to text translation,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Indic-TEDST: Datasets and baselines for low-resource speech to text translation,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.203682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3e9892e7-ce76-4871-86a0-97e6e10ffc60 · outbound

This paper cites Hy- brid ctc/attention architecture for end-to-end speech recognition,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data Hy- brid ctc/attention architecture for end-to-end speech recognition,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:00.870730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc8d094e-01c8-410b-b5d9-5792306d0622 · outbound

This paper cites BUT systems for IWSLT 2023 Marathi - Hindi low resource speech translation task,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data BUT systems for IWSLT 2023 Marathi - Hindi low resource speech translation task,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.185593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b3bdf6b5-b96c-4af4-aef5-a76f3a152185 · outbound

This paper cites w2v-bert: Combining contrastive learning and masked language modeling for self-supervised speech pre-training,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data w2v-bert: Combining contrastive learning and masked language modeling for self-supervised speech pre-training,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.174208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dfebce3c-51e4-4156-8df6-2c73b66b246e · outbound

This paper cites No Language Left Behind: Scaling Human-Centered Machine Translation.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T23:50:01.071296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb979a95-5fc2-4c5b-99ef-679f160a8f86 · outbound

This paper cites SentencePiece: A simple and lan- guage independent subword tokenizer and detokenizer for Neural Text Processing,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data SentencePiece: A simple and lan- guage independent subword tokenizer and detokenizer for Neural Text Processing,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.163550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5af425f2-e4a5-4b28-b414-d65c92a305c6 · outbound

This paper cites ESPnet-ST: All-in-one speech translation toolkit,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data ESPnet-ST: All-in-one speech translation toolkit,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.150747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 866a2fc1-3639-4557-b322-4fdd397710fc · outbound

This paper cites A Call for Clarity in Reporting BLEU Scores,.

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data A Call for Clarity in Reporting BLEU Scores,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:50:01.139091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 2f91e77d-577d-4024-8772-e556175274b0 · inbound