Paper Citation Record · LEDGER

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation

As of 20 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 2 inbound Pith citation observations for arXiv:2502.00377.

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

pith.paper-citation-record.v1
2502.00377 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T19:16:37.892896Z

measured 34 of 34 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:15:59.897627Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-16T21:51:17.764632Z

Reference resolution

32 of 32 outbound references displayed

verified exact5
verified fuzzy13
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 71a4c16e-6d47-4d59-83f2-85c970d3b612 · outbound

This paper cites Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.771901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c869978-87ae-4c77-b825-c11b644a453c · outbound

This paper cites Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.776878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73ac5f6b-8f20-45ee-a374-999f7122000d · outbound

This paper cites Leveraging weakly supervised data to improve end-to-end speech-to-text translation,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Leveraging weakly supervised data to improve end-to-end speech-to-text translation,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.275202Z

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 5b07f8f3-af5d-41cc-abea-f4bab83b0fed · outbound

This paper cites Analyzing asr pretraining for low-resource speech-to-text translation,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Analyzing asr pretraining for low-resource speech-to-text translation,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.263304Z

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 daa731d3-159c-40d9-b1a7-f4451858b50b · outbound

This paper cites Self-Training for End-to-End Speech Translation.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Self-Training for End-to-End Speech Translation

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-09T19:16:38.078778Z

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 16240c3b-62e8-424d-9fe3-98139f24601f · outbound

This paper cites Large-Scale Self- and Semi-Supervised Learning for Speech Translation.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Large-Scale Self- and Semi-Supervised Learning for Speech Translation

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-09T19:16:38.064399Z

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 3786c8b8-75f5-4085-8691-fc2d004b7c65 · outbound

This paper cites On the integration of speech recognition and statistical machine translation,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation On the integration of speech recognition and statistical machine translation,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.252457Z

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 93b24755-3919-408c-8fda-56b78a60279c · outbound

This paper cites Integrated n-best re-ranking for spoken language translation.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Integrated n-best re-ranking for spoken language translation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.241695Z

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 12c6dc73-2e67-4b66-b77c-3a881a428dbb · outbound

This paper cites Neural lattice search for speech recognition,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Neural lattice search for speech recognition,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.229768Z

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 f11eac98-c439-4b7b-ac42-470edb234e38 · outbound

This paper cites A new decoder for spoken language trans- lation based on confusion networks,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation A new decoder for spoken language trans- lation based on confusion networks,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.218253Z

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 ac714583-4672-4a1f-8f50-5b6f5e127649 · outbound

This paper cites Neural speech translation using lattice transformations and graph networks,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Neural speech translation using lattice transformations and graph networks,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.206776Z

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 781bcee2-c4d9-4ad0-a27e-a23ca24e31f0 · outbound

This paper cites Self-Attentional Models for Lattice Inputs.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Self-Attentional Models for Lattice Inputs

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-09T19:16:38.048825Z

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 d2c0d79c-189d-432b-a554-4febaf08f1ed · outbound

This paper cites Spoken language translation using automatically transcribed text in training,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Spoken language translation using automatically transcribed text in training,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.194270Z

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 1f39ced0-f968-4657-9838-e4139964e220 · outbound

This paper cites Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.825059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28afe047-e2aa-42cd-a049-22c8607830a9 · outbound

This paper cites Robust Neural Machine Translation for Clean and Noisy Speech Transcripts.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Robust Neural Machine Translation for Clean and Noisy Speech Transcripts

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-09T19:16:38.022516Z

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 e8f5904d-8cad-4feb-9970-f67b51a6c443 · outbound

This paper cites Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-09T19:16:38.006903Z

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 63be6bef-3aa4-4cb9-a139-eecf36350405 · outbound

This paper cites Fast-md: Fast multi-decoder end-to-end speech translation with non-autoregressive hidden intermediates,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Fast-md: Fast multi-decoder end-to-end speech translation with non-autoregressive hidden intermediates,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.183099Z

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 9ca7d3c5-2e50-42e4-8f3c-37a13f6c4f4f · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation On the Opportunities and Risks of Foundation Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.839958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ed147d5-4938-4c3f-9ed0-e93c9a35ff3f · outbound

This paper cites Pre-trained models: Past, present and future,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Pre-trained models: Past, present and future,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.843562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4cffacc-9597-448f-8c66-fdefb9c92978 · outbound

This paper cites WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.847173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62c0c51c-d45b-4131-a432-e44537495cef · outbound

This paper cites GigaST: A 10,000-hour Pseudo Speech Translation Corpus.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation GigaST: A 10,000-hour Pseudo Speech Translation Corpus

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.850653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bdf3221-04a5-491f-9226-7f8017b1ed4f · outbound

This paper cites Faster Algorithms for Longest Common Substring,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Faster Algorithms for Longest Common Substring,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.164596Z

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 af77003e-b8f4-4571-b116-5b776e43fa43 · outbound

This paper cites Direct speech-to-speech translation with discrete units.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Direct speech-to-speech translation with discrete units

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.857796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9442da8d-d099-405e-b24c-8dbec3965018 · outbound

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

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Hubert: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.861564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36a1a052-2da7-43d5-a94e-3fa582a15f61 · outbound

This paper cites SUPERB: Speech processing Universal PERformance Benchmark.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation SUPERB: Speech processing Universal PERformance Benchmark

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.865512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40867aa0-dbf6-4c5f-b4b6-8bab76284ec5 · outbound

This paper cites On gener- ative spoken language modeling from raw audio,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation On gener- ative spoken language modeling from raw audio,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.869345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 773af0ec-1f29-4a19-8d89-78a328d50aa4 · outbound

This paper cites Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.872786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 415b8310-443a-4da4-a44e-d58126dbd1d9 · outbound

This paper cites Speech-to-speech translation between untranscribed unknown languages,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Speech-to-speech translation between untranscribed unknown languages,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.139469Z

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 00e19668-e83b-41f8-aa38-448104400d91 · outbound

This paper cites Uwspeech: Speech to speech translation for unwritten languages,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Uwspeech: Speech to speech translation for unwritten languages,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.127604Z

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 c68a647c-86b7-4515-9d19-a420d719dd5a · outbound

This paper cites GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.885007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 365fdb58-83d0-4756-99da-81ddc14db160 · outbound

This paper cites VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T19:16:37.888931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc7f0ef0-03a1-4c49-adf1-441b037de1a1 · outbound

This paper cites Multilingual denoising pre-training for neural machine translation,.

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation Multilingual denoising pre-training for neural machine translation,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:16:38.115683Z

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.

Pith citing papers

Observation 0db557a4-ee39-43a5-af0a-938b1132a85a · inbound

It's Not a Walk in the Park! Challenges of Idiom Translation in Speech-to-text Systems cites this paper.

It's Not a Walk in the Park! Challenges of Idiom Translation in Speech-to-text Systems When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:59.897627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f40e10f-5ebd-426b-94cd-250e0379a231 · inbound

Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs cites this paper.

Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-16T21:51:17.766208Z

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.