Paper Citation Record · LEDGER

On the use of Performer and Agent Attention for Spoken Language Identification

As of 10 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2502.05841.

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

pith.paper-citation-record.v1
2502.05841 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T17:49:21.517630Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T17:49:21.367034Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-08T17:49:21.664257Z

Reference resolution

42 of 42 outbound references displayed

verified exact1
verified fuzzy24
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8057e781-0a87-41b4-bac9-793f7fbd9bae · outbound

This paper cites It is often used in applications like speech recogni- tion [1, 2], language translation [3], and content filtering [4].

On the use of Performer and Agent Attention for Spoken Language Identification It is often used in applications like speech recogni- tion [1, 2], language translation [3], and content filtering [4]

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:22.034081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 532e5be9-669f-41ad-98c8-ea5dce3ec6d7 · outbound

This paper cites an unresolved cited work.

On the use of Performer and Agent Attention for Spoken Language Identification Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:49:22.021212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5aa3a298-1c94-4e23-bdc6-1ebab25e88a4 · outbound

This paper cites Notations: We denote vectors and matrices by boldface low- ercase and uppercase letters, respectively.

On the use of Performer and Agent Attention for Spoken Language Identification Notations: We denote vectors and matrices by boldface low- ercase and uppercase letters, respectively

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:22.009662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ba651ae8-aa9d-4434-a355-19ce4c949deb · outbound

This paper cites On the use of Performer and Agent Attention for Spoken Language Identification.

On the use of Performer and Agent Attention for Spoken Language Identification On the use of Performer and Agent Attention for Spoken Language Identification

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-08-08T17:49:21.668705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 86a436cf-b926-49b0-b2e7-06ff79a0b0df · outbound

This paper cites We refer to the output of the pre-trained network (BEST-RQ) as the embedding sequence.

On the use of Performer and Agent Attention for Spoken Language Identification We refer to the output of the pre-trained network (BEST-RQ) as the embedding sequence

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.997468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b7f85a76-ac86-42c6-97a4-3f4fb272c310 · outbound

This paper cites an unresolved cited work.

On the use of Performer and Agent Attention for Spoken Language Identification Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:49:21.986102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c5a89950-c1a1-4f77-b58e-6971a2abe935 · outbound

This paper cites The computational complexity for both Eq.

On the use of Performer and Agent Attention for Spoken Language Identification The computational complexity for both Eq

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.974888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 76191da1-053a-4b6f-b4aa-5ddbeb45c21a · outbound

This paper cites an unresolved cited work.

On the use of Performer and Agent Attention for Spoken Language Identification Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-08T17:49:21.962626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b76baac1-5f5d-4b75-91c2-1fddb7996b24 · outbound

This paper cites Typically, the agent matrix is given byG = Pooling(Q) (Sec- tion 4.4).

On the use of Performer and Agent Attention for Spoken Language Identification Typically, the agent matrix is given byG = Pooling(Q) (Sec- tion 4.4)

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.950793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 325ffd1b-c2b5-459c-aa49-b7460b668f8b · outbound

This paper cites Dataset Pre-training Data: We utilized the open-source V oxPopuli dataset [25] for pre-training the BEST-RQ model.

On the use of Performer and Agent Attention for Spoken Language Identification Dataset Pre-training Data: We utilized the open-source V oxPopuli dataset [25] for pre-training the BEST-RQ model

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.939691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 19ccb65c-a7a2-4404-842e-f1129d6e873d · outbound

This paper cites These results are reported in Table-4.

On the use of Performer and Agent Attention for Spoken Language Identification These results are reported in Table-4

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.926383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 96973d07-7356-46d7-87b3-ef9a28e6f04c · outbound

This paper cites In particu- lar, we demonstrated the effectiveness of performer- and agent- attention over self-attention for language identification in a self- supervised learning paradigm.

On the use of Performer and Agent Attention for Spoken Language Identification In particu- lar, we demonstrated the effectiveness of performer- and agent- attention over self-attention for language identification in a self- supervised learning paradigm

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.914433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e2dae1cf-4ce4-48f4-81a8-f1c3faf77b94 · outbound

This paper cites Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification.

On the use of Performer and Agent Attention for Spoken Language Identification Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-08T17:49:21.651792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8fceb7a0-ffb7-497b-a1a7-a1894d06c4c4 · outbound

This paper cites A real-time end-to-end multi- lingual speech recognition architecture,.

On the use of Performer and Agent Attention for Spoken Language Identification A real-time end-to-end multi- lingual speech recognition architecture,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.900429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16116d8e-66f3-45fd-9a90-36690f13a1e2 · outbound

This paper cites Transformer-based machine translation for low- resourced languages embedded with language identification,.

On the use of Performer and Agent Attention for Spoken Language Identification Transformer-based machine translation for low- resourced languages embedded with language identification,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.888315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7deb1654-d7d6-47c8-8675-ee9a757864f7 · outbound

This paper cites Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus.

On the use of Performer and Agent Attention for Spoken Language Identification Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.415485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc493032-7ee5-4967-bcb5-88206b308a26 · outbound

This paper cites Language and dialect identification: A survey,.

On the use of Performer and Agent Attention for Spoken Language Identification Language and dialect identification: A survey,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.875055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 189ded9e-12b3-415b-a425-15f4e8764a59 · outbound

This paper cites Language identifica- tion from short segments of speech,.

On the use of Performer and Agent Attention for Spoken Language Identification Language identifica- tion from short segments of speech,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.862243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f290227c-b5c5-4795-a280-89e19690fa00 · outbound

This paper cites Self-supervised learning: Generative or contrastive,.

On the use of Performer and Agent Attention for Spoken Language Identification Self-supervised learning: Generative or contrastive,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.849002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 11d5094d-060e-4c0e-b8af-16e15e44cf58 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

On the use of Performer and Agent Attention for Spoken Language Identification Representation Learning with Contrastive Predictive Coding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.431222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3270eb35-c081-43cf-a4f1-a0d056fd4f2c · outbound

This paper cites wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,.

On the use of Performer and Agent Attention for Spoken Language Identification wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.435435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cae2ffc-e533-4d71-a864-a69adc2e2d73 · outbound

This paper cites W2v-bert: Combining contrastive learning and masked language modeling for self-supervised speech pre-training,.

On the use of Performer and Agent Attention for Spoken Language Identification W2v-bert: Combining contrastive learning and masked language modeling for self-supervised speech pre-training,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.827272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 62f2448b-646d-46ff-a5bf-5cec36c3cc0a · outbound

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

On the use of Performer and Agent Attention for Spoken Language Identification Hubert: Self-supervised speech rep- resentation learning by masked prediction of hidden units,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.442920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b38d37f9-6233-41f8-ad1b-955ccf383322 · outbound

This paper cites Efficient self-supervised learning rep- resentations for spoken language identification,.

On the use of Performer and Agent Attention for Spoken Language Identification Efficient self-supervised learning rep- resentations for spoken language identification,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.807186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 098865ab-9758-4666-bbc4-e67a3b95e6ee · outbound

This paper cites Asbert: Asr-specific self-supervised learning with self-training,.

On the use of Performer and Agent Attention for Spoken Language Identification Asbert: Asr-specific self-supervised learning with self-training,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.795923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2cd7532b-de92-4005-ae0a-81001c6275c3 · outbound

This paper cites Self-supervised learning with random-projection quantizer for speech recogni- tion,.

On the use of Performer and Agent Attention for Spoken Language Identification Self-supervised learning with random-projection quantizer for speech recogni- tion,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.454559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bc83160-5eec-40a8-8ab1-7d8ae45fbccc · outbound

This paper cites Attention mechanisms in computer vision: A survey,.

On the use of Performer and Agent Attention for Spoken Language Identification Attention mechanisms in computer vision: A survey,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.777072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 27119e78-2232-4d05-8ab0-9e3bce195e46 · outbound

This paper cites An introductory survey on attention mechanisms in NLP problems,.

On the use of Performer and Agent Attention for Spoken Language Identification An introductory survey on attention mechanisms in NLP problems,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.765174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c16d742c-8fae-462a-af19-7953f3add36a · outbound

This paper cites A Survey on Efficient Training of Transformers.

On the use of Performer and Agent Attention for Spoken Language Identification A Survey on Efficient Training of Transformers

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.465903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 005f9ad5-9ecf-4a54-96d4-06a34f5b9cc5 · outbound

This paper cites Rethinking Attention with Performers.

On the use of Performer and Agent Attention for Spoken Language Identification Rethinking Attention with Performers

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.470098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e4e075c-df47-4e25-a287-ec792cd81619 · outbound

This paper cites Agent Attention: On the Integration of Softmax and Linear Attention.

On the use of Performer and Agent Attention for Spoken Language Identification Agent Attention: On the Integration of Softmax and Linear Attention

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.474356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 315fa50d-0667-4088-bad9-95df9f9bb6a7 · outbound

This paper cites Attentive Statistics Pooling for Deep Speaker Embedding.

On the use of Performer and Agent Attention for Spoken Language Identification Attentive Statistics Pooling for Deep Speaker Embedding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.478300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30731ae2-b175-40f1-8993-4182b8f77fea · outbound

This paper cites On the performance of time-pooling strategies for end-to-end spoken language identifi- cation,.

On the use of Performer and Agent Attention for Spoken Language Identification On the performance of time-pooling strategies for end-to-end spoken language identifi- cation,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.752661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 21531f14-1c36-4497-be21-79d70104ea23 · outbound

This paper cites Attentive temporal pooling for conformer-based streaming lan- guage identification in long-form speech,.

On the use of Performer and Agent Attention for Spoken Language Identification Attentive temporal pooling for conformer-based streaming lan- guage identification in long-form speech,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.740600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 672fb68b-9f97-44b0-8f4b-7027021fdd78 · outbound

This paper cites Attention is all you need,.

On the use of Performer and Agent Attention for Spoken Language Identification Attention is all you need,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.489893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68379854-5ae8-4b2e-b93c-4f07058dbfe8 · outbound

This paper cites Flatten trans- former: Vision transformer using focused linear attention,.

On the use of Performer and Agent Attention for Spoken Language Identification Flatten trans- former: Vision transformer using focused linear attention,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.719915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4ca6cc9-34e4-439c-b240-26c98d0a3493 · outbound

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

On the use of Performer and Agent Attention for Spoken Language Identification VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.497522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa24865a-073b-4843-b24d-718cc30acc56 · outbound

This paper cites V oxlingua107: a dataset for spoken lan- guage recognition,.

On the use of Performer and Agent Attention for Spoken Language Identification V oxlingua107: a dataset for spoken lan- guage recognition,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.707436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c39c3631-94d8-4b54-803f-2b7a0b8483dc · outbound

This paper cites Fleurs: Few-shot learning evaluation of universal representations of speech,.

On the use of Performer and Agent Attention for Spoken Language Identification Fleurs: Few-shot learning evaluation of universal representations of speech,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.693948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8f0e79bc-f485-45bc-8741-07f7b193a908 · outbound

This paper cites Swish: a self-gated activation function,.

On the use of Performer and Agent Attention for Spoken Language Identification Swish: a self-gated activation function,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:49:21.681239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 233e3165-be40-40f1-8f47-d99b550e6d1e · outbound

This paper cites Adam: A Method for Stochastic Optimization.

On the use of Performer and Agent Attention for Spoken Language Identification Adam: A Method for Stochastic Optimization

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.513808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a93d007a-4023-429f-8993-7156ec867d7d · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

On the use of Performer and Agent Attention for Spoken Language Identification BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-08T17:49:21.517630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ba651ae8-aa9d-4434-a355-19ce4c949deb · inbound