Paper Citation Record · LEDGER

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR

As of 22 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2506.19761.

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

pith.paper-citation-record.v1
2506.19761 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:31:06.776115Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:31:06.652611Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T18:31:06.981463Z

Reference resolution

44 of 44 outbound references displayed

verified exact3
verified fuzzy19
unresolved20
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 978480a1-5261-4599-ab02-70a9963c077c · outbound

This paper cites However, Transformers, especially their multi-head attention (MHA) component, are ill-suited for long- form ASR due to quadratic time/memory complexity in se- quence length.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR However, Transformers, especially their multi-head attention (MHA) component, are ill-suited for long- form ASR due to quadratic time/memory complexity in se- quence length

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.279745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c56b04a4-d102-47f2-8ed6-c78a1e85c1e2 · outbound

This paper cites Recently, several layer types have been introduced that mimic the properties of MHA while having linear time and memory complexity in sequence length.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Recently, several layer types have been introduced that mimic the properties of MHA while having linear time and memory complexity in sequence length

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.270003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0556f91a-3218-43bf-87d8-759f10403329 · outbound

This paper cites Bidi- rectional RWKV-Conformer is more efficient than standard Conformer and limited-context attention with global tokens.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Bidi- rectional RWKV-Conformer is more efficient than standard Conformer and limited-context attention with global tokens

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.259165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c5c4f5b4-b1f4-4ce5-89f3-a99fb58b3dc8 · outbound

This paper cites an unresolved cited work.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:31:07.216044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 54d97e29-6144-4be8-8d8a-ef2e8daa8ef8 · outbound

This paper cites an unresolved cited work.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:31:07.236777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 30e807e7-b7cd-4dfe-85db-0d8e50b8f6a6 · outbound

This paper cites an unresolved cited work.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:31:07.247044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0b2428a1-5cec-48db-91c2-3f3886bdef7b · outbound

This paper cites an unresolved cited work.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:31:07.226697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b17b0a7f-f1f3-4141-8b9e-5a2ea6f8e74c · outbound

This paper cites Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T18:31:06.984960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f9fbea96-0b35-447a-8b8b-27e43f77e65e · outbound

This paper cites For all models in this paper, we maintain the same overall architecture, the same Conformer layer structure, and the same parameters for all convolutional and linear layers.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR For all models in this paper, we maintain the same overall architecture, the same Conformer layer structure, and the same parameters for all convolutional and linear layers

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.203246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5d87758b-0080-4f0c-adca-e30cce1f4590 · outbound

This paper cites SF” (short-form), we performed training on the stan- dard segments released with the dataset, which have an average length of 4.4 seconds. For long-form training (“LF.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR SF” (short-form), we performed training on the stan- dard segments released with the dataset, which have an average length of 4.4 seconds. For long-form training (“LF

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.191568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 36b18f25-ded7-41a8-a761-f142b8e84e9d · outbound

This paper cites Short-Form ASR Table 1: MHA vs.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Short-Form ASR Table 1: MHA vs

Reference 11

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T18:31:07.180649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 92d8ce2c-3b7f-48de-a52b-7db93f5bc23e · outbound

This paper cites Our bi-RWKV- Conformer matches or exceeds MHA and limited-context MHA accuracy, while processing more audio per second.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Our bi-RWKV- Conformer matches or exceeds MHA and limited-context MHA accuracy, while processing more audio per second

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.169593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 95d28f30-37d1-4977-bd8c-f8330285c00e · outbound

This paper cites Robust Speech Recognition via Large-Scale Weak Supervision.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Robust Speech Recognition via Large-Scale Weak Supervision

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.669637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d20eee8-ac63-4f62-97bd-c5c67c3d2ad4 · outbound

This paper cites RWKV: Reinventing RNNs for the Transformer Era.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR RWKV: Reinventing RNNs for the Transformer Era

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.673368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a897cf3a-9733-4698-8043-244304e1ea88 · outbound

This paper cites Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.676738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1590affa-4176-4a70-975a-84ba1f29b038 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.680257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d611bead-e870-4a95-b2ce-1f440c62bf22 · outbound

This paper cites Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.683772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3179b27c-eb56-46be-b07a-ecf0eb990b66 · outbound

This paper cites Investigating end-to-end ASR architectures for long form audio transcription,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Investigating end-to-end ASR architectures for long form audio transcription,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.158012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e42bf6c7-41da-4718-8478-9c047fea47c5 · outbound

This paper cites Efficiently Modeling Long Sequences with Structured State Spaces.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Efficiently Modeling Long Sequences with Structured State Spaces

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.691266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33e06311-7e2f-47c6-bdb2-9e31b006639e · outbound

This paper cites Hungry Hungry Hippos: Towards Language Modeling with State Space Models.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Hungry Hungry Hippos: Towards Language Modeling with State Space Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.694841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d8a6bf0-a1c9-4531-b00e-c4a05937344b · outbound

This paper cites Multi-Head State Space Model for Speech Recognition.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Multi-Head State Space Model for Speech Recognition

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:31:06.898024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0f33a68c-53f9-489a-804b-095f19b5904b · outbound

This paper cites Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:31:06.882764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d741bf5e-4065-4086-b045-1198dc6931e3 · outbound

This paper cites Structured state space decoder for speech recognition and synthesis,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Structured state space decoder for speech recognition and synthesis,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.706237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41516056-229f-4453-9efc-668ef57618f6 · outbound

This paper cites Exploring RWKV for Memory Efficient and Low Latency Streaming ASR.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Exploring RWKV for Memory Efficient and Low Latency Streaming ASR

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.709387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 315401b0-09e5-40d3-a0ae-12a78360bf37 · outbound

This paper cites Augmenting conformers with structured state-space sequence models for online speech recognition,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Augmenting conformers with structured state-space sequence models for online speech recognition,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.137397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 988f1aa3-50a6-4154-a733-b5f892d7fa08 · outbound

This paper cites Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.715445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd87678e-cd4c-4c6e-ae03-ca2464f2ffb8 · outbound

This paper cites Exploring the ca- pability of Mamba in speech applications,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Exploring the ca- pability of Mamba in speech applications,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.127030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 070a5b32-97b5-46c1-97d8-e8458a6c8045 · outbound

This paper cites Updated corpora and benchmarks for long-form speech recognition,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Updated corpora and benchmarks for long-form speech recognition,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.116261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 04601339-36a5-48ac-af54-e204d23ce140 · outbound

This paper cites Learning with marginalized corrupted features,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Learning with marginalized corrupted features,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.105014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation dae28afe-43e8-4ec8-bf82-93045eeb14e7 · outbound

This paper cites Dropout training as adaptive regularization,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Dropout training as adaptive regularization,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.093758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c8492993-38ac-43f4-9877-bf0c6917a9e6 · outbound

This paper cites Learning with pseudo- ensembles,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Learning with pseudo- ensembles,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.083659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 34de8f47-86b4-43e2-ac29-c2bc08c19262 · outbound

This paper cites Structured reg- ularizer for neural higher-order sequence models,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Structured reg- ularizer for neural higher-order sequence models,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.073345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 69d091a5-3a59-4938-a216-b44c838dbf6c · outbound

This paper cites Improving neural networks by preventing co-adaptation of feature detectors.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Improving neural networks by preventing co-adaptation of feature detectors

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.736523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 009f333d-0251-402c-92e8-473d71f7c82d · outbound

This paper cites Regularization of neural networks using dropconnect,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Regularization of neural networks using dropconnect,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.061646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fbcabdca-b929-47f7-9445-2c0315709239 · outbound

This paper cites Reducing transformer depth on demand with structured dropout,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Reducing transformer depth on demand with structured dropout,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.048157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation db08eddd-405e-4b08-819c-fc94cf697ced · outbound

This paper cites Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:31:06.835711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5bd2d4eb-3fb8-45cf-bbd1-79bed895409f · outbound

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

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Conformer: Convolution-augmented transformer for speech recognition,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.749822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d168ca7-2bc7-47bb-aeff-d11f5537d1c6 · outbound

This paper cites Sequence transduction with recurrent neural networks,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Sequence transduction with recurrent neural networks,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.753135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 767ff59f-7770-4fb6-b85f-eef5554282ab · outbound

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

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Fast conformer with linearly scalable attention for efficient speech recognition,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.757022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8f29d9f-ae71-460b-a54c-30b60262d6d0 · outbound

This paper cites Bidirectional recurrent neu- ral networks,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Bidirectional recurrent neu- ral networks,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.017587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e7a8ee77-f2ae-4ad0-bdc0-b0d27260d94d · outbound

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

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR WeNet: Production oriented stream- ing and non-streaming end-to-end speech recognition toolkit,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:07.006805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bc128536-7e4a-444c-b2c8-802a7ecb741a · outbound

This paper cites WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.768804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 726d0962-9e89-45da-ac68-eea2469fd025 · outbound

This paper cites Longformer: The Long-Document Transformer.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Longformer: The Long-Document Transformer

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T18:31:06.772280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bbab7dd-478a-4287-a248-5981f0ccf767 · outbound

This paper cites Earnings-21: A practical benchmark for ASR in the wild,.

Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Earnings-21: A practical benchmark for ASR in the wild,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:31:06.995026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Pith citing papers

Observation b17b0a7f-f1f3-4141-8b9e-5a2ea6f8e74c · inbound