Paper Citation Record · LEDGER

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization

As of 6 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 1 inbound Pith citation observation for arXiv:2604.19079.

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

pith.paper-citation-record.v1
2604.19079 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T01:47:03.235861Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T01:47:03.235861Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-11T13:26:03.348845Z

Reference resolution

34 of 34 outbound references displayed

verified exact1
verified fuzzy30
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5a0e9b97-9396-41a0-b7a9-5a813c01bb9f · outbound

This paper cites Maintaining separate mod- els for these regimes increases the cost of model development, training, validation, and deployment.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Maintaining separate mod- els for these regimes increases the cost of model development, training, validation, and deployment

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.610699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0fe22f78-a54a-43e3-817d-d4a0d220b22d · outbound

This paper cites Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization

Reference 2

Resolution: malformed identifier; local_arxiv, observed 2026-05-11T13:26:03.421215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7a916ad2-17fa-4a60-951b-e35c823e4abe · outbound

This paper cites ASR modeling and evaluation As the main ASR architecture, we used RNNT model based on FastConformer encoder [22] with 123M parameters.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization ASR modeling and evaluation As the main ASR architecture, we used RNNT model based on FastConformer encoder [22] with 123M parameters

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.616207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7001dd21-4f8f-4596-b8f4-51578eb47c81 · outbound

This paper cites Table 2:Average WER (%) on Open ASR Leaderboard for dif- ferent training configurations of KLD teacher, KLD weightλ, and offlineαfor the same unified RNNT L-size model.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Table 2:Average WER (%) on Open ASR Leaderboard for dif- ferent training configurations of KLD teacher, KLD weightλ, and offlineαfor the same unified RNNT L-size model

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.593819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b7ab65a5-f4ab-471f-8522-13e1e6e6cb70 · outbound

This paper cites an unresolved cited work.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-05-23T02:07:23.620568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a9680ecf-2202-4d77-87f0-804fc2a757e1 · outbound

This paper cites Transformer Transducer: One Model Unifying Streaming and Non-streaming Speech Recognition.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Transformer Transducer: One Model Unifying Streaming and Non-streaming Speech Recognition

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:26:03.447915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fa1eb276-70ae-4dbb-8ac8-a3f294f5672b · outbound

This paper cites Dual-mode asr: Unify and improve streaming asr with full-context modeling.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Dual-mode asr: Unify and improve streaming asr with full-context modeling

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.604586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ec27f46f-5a9d-4e4e-b085-c2c257d1d90a · outbound

This paper cites Wenet: Production oriented stream- ing and non-streaming end-to-end speech recognition toolkit.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Wenet: Production oriented stream- ing and non-streaming end-to-end speech recognition toolkit

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.586202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3035961e-8355-496d-afa1-808e56c0158d · outbound

This paper cites Learning a dual-mode speech recognition model via self-pruning.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Learning a dual-mode speech recognition model via self-pruning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.613181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 29b4fca5-0fd6-4b84-ba94-bc065d0e025c · outbound

This paper cites Sequence transduction with recurrent neural net- works.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Sequence transduction with recurrent neural net- works

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.601955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a53f6930-3c93-4ff8-81c9-4e223b9edbb1 · outbound

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

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Conformer: Convolution- augmented transformer for speech recognition

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.623009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 833aa68a-8237-4915-a517-e66b0d66bab0 · outbound

This paper cites Developing real- time streaming transformer transducer for speech recognition on large-scale dataset.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Developing real- time streaming transformer transducer for speech recognition on large-scale dataset

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.596687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e3c33d65-765a-4611-b39a-bff56ca7c447 · outbound

This paper cites Streaming automatic speech recognition with the transformer model.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Streaming automatic speech recognition with the transformer model

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.607207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5fb9a430-8c21-4714-8022-223b8f48beb3 · outbound

This paper cites Stateful conformer with cache-based inference for streaming au- tomatic speech recognition.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Stateful conformer with cache-based inference for streaming au- tomatic speech recognition

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.583486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 092948d5-f0fc-4285-9fb7-521acd22b44b · outbound

This paper cites Unifying streaming and non- streaming zipformer-based asr.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Unifying streaming and non- streaming zipformer-based asr

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.599276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 63ac49dd-e824-4c4a-a7cd-bc33e65cf2bb · outbound

This paper cites Improving streaming speech recognition with time-shifted contextual attention and dynamic right context masking.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Improving streaming speech recognition with time-shifted contextual attention and dynamic right context masking

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.589712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cbae1eba-94c2-4009-b103-53c25b31b019 · outbound

This paper cites Dynamic chunk convolution for unified streaming and non- streaming conformer asr.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Dynamic chunk convolution for unified streaming and non- streaming conformer asr

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.562082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 400f8ab1-831c-49c1-82b6-d2c4c899a51e · outbound

This paper cites All-in-one asr: Unifying encoder-decoder models of ctc, attention, and transducer in dual-mode asr.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization All-in-one asr: Unifying encoder-decoder models of ctc, attention, and transducer in dual-mode asr

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.567046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 97b0f8ef-d1e9-489e-9282-c9cf91535157 · outbound

This paper cites Open asr leaderboard: Towards reproducible and transparent multilingual and long-form speech recognition evaluation.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Open asr leaderboard: Towards reproducible and transparent multilingual and long-form speech recognition evaluation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.559521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ae443cfa-7eeb-4abe-9a04-de4b11610f09 · outbound

This paper cites Parakeet tdt 0.6b v2 (en).

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Parakeet tdt 0.6b v2 (en)

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.546300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f96c9db7-c87b-4b13-b160-1910750ad8b6 · outbound

This paper cites Nemotron-speech-streaming-en-0.6b.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Nemotron-speech-streaming-en-0.6b

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.538852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dc2a0381-aba3-4efa-b9dd-6a061c8c9b2b · outbound

This paper cites Cr-ctc: Consistency regularization on ctc for improved speech recognition.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Cr-ctc: Consistency regularization on ctc for improved speech recognition

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.575335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bbe18c61-afec-43cc-8209-36115b14a8a2 · outbound

This paper cites Transducer consistency regularization for speech to text applications.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Transducer consistency regularization for speech to text applications

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.543958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2c0d6c42-8f77-48b4-9d11-79524cd852d0 · outbound

This paper cites PyTorch: An imperative style, high-performance deep learning library.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization PyTorch: An imperative style, high-performance deep learning library

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.578238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation af832611-0b18-47a6-98ad-1f900f87b678 · outbound

This paper cites Triton: an intermediate lan- guage and compiler for tiled neural network computations.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Triton: an intermediate lan- guage and compiler for tiled neural network computations

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.554271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f738d319-8732-4d1e-be6d-8d928586a416 · outbound

This paper cites Nemo: a toolkit for building ai applications using neural modules.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Nemo: a toolkit for building ai applications using neural modules

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.569634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6a39330b-4291-409d-8c63-4d6b64658b0a · outbound

This paper cites Fast Conformer with linearly scalable attention for efficient speech recognition.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Fast Conformer with linearly scalable attention for efficient speech recognition

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.556967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 86fc8a50-d4e9-4e34-a8fc-6fc6dd043dfc · outbound

This paper cites Emmett: Effi- cient multimodal machine translation training.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Emmett: Effi- cient multimodal machine translation training

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.541550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f578bb0b-376a-4004-9120-94e7787b9c58 · outbound

This paper cites Granary: Speech Recognition and Translation Dataset in 25 European Languages.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Granary: Speech Recognition and Translation Dataset in 25 European Languages

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T13:26:03.474898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5b60e12e-f009-4abe-989d-21537cfa19d9 · outbound

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

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Neural machine transla- tion of rare words with subword units

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.548762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8edf0d54-0c5c-483e-baca-ef6d537e2ec4 · outbound

This paper cites Label-looping: Highly efficient decoding for transducers.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Label-looping: Highly efficient decoding for transducers

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.564372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cf4554d8-5427-4193-a77d-21daf4800e71 · outbound

This paper cites Speed of light ex- act greedy decoding for rnn-t speech recognition models on gpu.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Speed of light ex- act greedy decoding for rnn-t speech recognition models on gpu

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.580879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bc272f0b-8589-4837-933c-14498bc96641 · outbound

This paper cites Transformers are ssms: Generalized models and efficient algorithms through structured state space duality.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Transformers are ssms: Generalized models and efficient algorithms through structured state space duality

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.551623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6ee0f541-e656-46e9-9fdf-cd11a2d8c504 · outbound

This paper cites Canary-qwen-2.5b.

Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization Canary-qwen-2.5b

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-23T02:07:23.572658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 0fe22f78-a54a-43e3-817d-d4a0d220b22d · inbound