Paper Citation Record · LEDGER

Right Label Context in End-to-End Training of Time-Synchronous ASR Models

As of 23 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 1 inbound Pith citation observation for arXiv:2501.04521.

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

pith.paper-citation-record.v1
2501.04521 v2

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T21:34:36.388230Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-10T20:25:33.127942Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T20:27:36.589504Z

Reference resolution

34 of 34 outbound references displayed

verified exact2
verified fuzzy30
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4b5b5192-4e8d-47e7-9acc-4999b40153fe · outbound

This paper cites Connection- ist temporal classiﬁcation: labelling unsegmented sequen ce data with recurrent neural networks,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Connection- ist temporal classiﬁcation: labelling unsegmented sequen ce data with recurrent neural networks,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.861993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6e2dddb1-adbe-4656-af0e-3417f5d16f98 · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Sequence Transduction with Recurrent Neural Networks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T21:34:36.253848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42052eb8-8c27-468a-a0a0-e1e2daecf71d · outbound

This paper cites Monotonic recu rrent neural network transducer and decoding strategies,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Monotonic recu rrent neural network transducer and decoding strategies,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.848808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4a34e7cf-0eae-4cf8-9a01-0488113baf35 · outbound

This paper cites H MM vs. CTC for Automatic Speech Recognition: Comparison Based on F ull- Sum Training from Scratch,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models H MM vs. CTC for Automatic Speech Recognition: Comparison Based on F ull- Sum Training from Scratch,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.836828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ecfef1e2-e29d-471b-92bc-bd04606be8bb · outbound

This paper cites an unresolved cited work.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-10T21:34:36.824873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6b1c0039-a83b-4129-8cc3-1a1cee437a4e · outbound

This paper cites Neural machine tra nslation of rare words with subword units,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Neural machine tra nslation of rare words with subword units,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.811909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 13a891c8-b96c-4cd8-a1e5-f88ac4b28655 · outbound

This paper cites Multitask lear ning of context- dependent targets in deep neural network acoustic models,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Multitask lear ning of context- dependent targets in deep neural network acoustic models,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.800261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 21f54064-2dd3-4acf-842b-cc7d124d6dea · outbound

This paper cites Context-de pendent acoustic modeling without explicit phone clustering,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Context-de pendent acoustic modeling without explicit phone clustering,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.785201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3426bffa-f777-42d8-98f4-7172672b56e4 · outbound

This paper cites RNN- transducer with stateless prediction network,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models RNN- transducer with stateless prediction network,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.770588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2ff99f79-9641-439c-b0fa-02f034008fa9 · outbound

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

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Zipformer: A faster and better encoder for automatic speech recognition,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.755823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 748969ed-ce33-4507-b6a5-8b635c7b8417 · outbound

This paper cites Phoneme ba sed neural transducer for large vocabulary speech recognition,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Phoneme ba sed neural transducer for large vocabulary speech recognition,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.743163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 514a7b2a-6069-468d-b639-bf13b7a7bc31 · outbound

This paper cites Global normalization for streaming speech recogn ition in a modular framework,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Global normalization for streaming speech recogn ition in a modular framework,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.729462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2453f992-d550-4548-985b-cb448a79cbb0 · outbound

This paper cites Towards Consistent Hybrid HMM Acoustic Modeling.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Towards Consistent Hybrid HMM Acoustic Modeling

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-10T21:34:36.445733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ea190225-4ee1-4a2e-a463-8ee75ca508c8 · outbound

This paper cites Conformer: Convolutio n- Augmented Transformer for Speech Recognition,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Conformer: Convolutio n- Augmented Transformer for Speech Recognition,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.717861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c7eafc15-13db-4318-9231-11ea4ec66244 · outbound

This paper cites Competitive and resource efﬁcient factored hybrid HMM systems are simpl er than you think,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Competitive and resource efﬁcient factored hybrid HMM systems are simpl er than you think,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.705177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d4ea37fd-2223-4e07-8d50-eed73406601a · outbound

This paper cites CDNN : A context dependent neural network for continuous speech recognitio n,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models CDNN : A context dependent neural network for continuous speech recognitio n,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.692842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e032a9c1-97c3-4458-9eb7-3598027c6ef1 · outbound

This paper cites HMM vs. CTC for automatic speech recognition: Comparison based on f ull-sum training from scratch,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models HMM vs. CTC for automatic speech recognition: Comparison based on f ull-sum training from scratch,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.680793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1934f727-8935-4eb3-aab0-2cbd28153504 · outbound

This paper cites Weighted ﬁnite-sta te transducers in speech recognition,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Weighted ﬁnite-sta te transducers in speech recognition,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.669010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3d6b370c-8953-4ad9-9fab-5812eb3fda1b · outbound

This paper cites Regarding topology and variant fra me rates for differentiable WFST-based end-to-end asr,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Regarding topology and variant fra me rates for differentiable WFST-based end-to-end asr,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.657432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 84b6171d-bc8e-46d9-8550-ca60e300fc05 · outbound

This paper cites CTC in the co ntext of generalized full-sum HMM training,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models CTC in the co ntext of generalized full-sum HMM training,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.645121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f5fa6b54-4b9d-4fb7-b3f8-017fd5cffb20 · outbound

This paper cites Investigating the effect of label topology and training criterion on asr pe rformance and alignment quality,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Investigating the effect of label topology and training criterion on asr pe rformance and alignment quality,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.631536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d4818f61-8556-49d5-87a5-7fce9a915400 · outbound

This paper cites Tree-based state tying for high accuracy acoustic modelling,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Tree-based state tying for high accuracy acoustic modelling,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.619003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f20a9d58-6eae-4e4e-aeec-2808c4281c15 · outbound

This paper cites Switchboard : Telephone Speech Corpus for Research and Development,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Switchboard : Telephone Speech Corpus for Research and Development,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.606897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f77601fc-8ca0-47ef-89cf-f8e53b32d924 · outbound

This paper cites Libr iSpeech: An ASR Corpus Based on Public Domain Audio Books,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Libr iSpeech: An ASR Corpus Based on Public Domain Audio Books,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.594196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 64ed2ed2-c9bc-4e5d-a81a-665e8c7380fe · outbound

This paper cites RETURNN: The RWTH extensible training framework for unive rsal recurrent neural networks,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models RETURNN: The RWTH extensible training framework for unive rsal recurrent neural networks,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.581250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2461d4c6-c100-4e94-a477-c7623696ae20 · outbound

This paper cites RASR-the RWTH Aachen u ni- versity open source speech recognition toolkit,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models RASR-the RWTH Aachen u ni- versity open source speech recognition toolkit,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.567717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 25179f24-2f88-4c14-9086-280c83c2aaaa · outbound

This paper cites RA SR2: The RWTH ASR toolkit for generic sequence-to-sequence speech r ecogni- tion,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models RA SR2: The RWTH ASR toolkit for generic sequence-to-sequence speech r ecogni- tion,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.554140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7d34f993-c345-490b-a0ef-de982e80eadc · outbound

This paper cites Sisyphus, a workﬂow ma nager designed for machine translation and automatic speech reco gnition,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Sisyphus, a workﬂow ma nager designed for machine translation and automatic speech reco gnition,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.541374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a3176f0b-b1f7-4799-9804-17656ecd0747 · outbound

This paper cites Gamma tone features and feature combination for large vocabulary speech recogn ition,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Gamma tone features and feature combination for large vocabulary speech recogn ition,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.527462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 88db6780-e84f-43c3-bc25-5c77f0046b79 · outbound

This paper cites SpecAugment on Large Scale Datasets,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models SpecAugment on Large Scale Datasets,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.514550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7d3c61b0-964d-45ea-9563-d9f44c082871 · outbound

This paper cites Efficient Training of Neural Transducer for Speech Recognition.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Efficient Training of Neural Transducer for Speech Recognition

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-10T21:34:36.427499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ba0b36b3-e216-49f2-87f5-cfe87455457f · outbound

This paper cites Conformer: Convolution-augme nted Transformer for Speech Recognition,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Conformer: Convolution-augme nted Transformer for Speech Recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.500055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 402b8d24-fa3e-45cf-b0a1-95ce71a27605 · outbound

This paper cites Super-convergence: V ery f ast training of neural networks using large learning rates,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Super-convergence: V ery f ast training of neural networks using large learning rates,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.485998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4281a5f4-a019-48a2-8cb2-068414736169 · outbound

This paper cites Incorporating Nesterov Momentum into Adam,.

Right Label Context in End-to-End Training of Time-Synchronous ASR Models Incorporating Nesterov Momentum into Adam,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:34:36.472700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation b5413ae3-61ac-42fb-8423-5534e301fb5b · inbound

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs cites this paper.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Right Label Context in End-to-End Training of Time-Synchronous ASR Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.590845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.