Pith. sign in

Paper Citation Record · LEDGER

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition

As of 22 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2607.29279.

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

pith.paper-citation-record.v1
2607.29279 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T10:13:57.954776Z

measured 41 of 41 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

41 of 41 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved41
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 786023c1-079a-4bf8-82c1-d41f5b28afd8 · outbound

This paper cites arXiv preprint arXiv:2509.12508 (2025).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition arXiv preprint arXiv:2509.12508 (2025)

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:53.900211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:53.900211Z digest=sha256:dcf106e761b866d3e969f7d55c1d8ec45a85ee7cbc2e84a00d2bf33abc07e4fc

Observation 98d73dab-bdee-4925-b285-723f707ab2c4 · outbound

This paper cites In: Proceedings of the Twelfth Language Resources and Evaluation Conference.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: Proceedings of the Twelfth Language Resources and Evaluation Conference

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:53.962467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:53.962467Z digest=sha256:4504543929838ee27635dc6488112b13811677f0f990ee73dc91ac000dc24f5e

Observation 59897fb3-9159-4e10-b6ff-cd66f47b02d4 · outbound

This paper cites an unresolved cited work.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Unresolved cited work

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:54.044695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:54.044695Z digest=sha256:7359b787d1162f7a4b4215086b19bc7ccc9661ddc058a805a1d0f88671ebc7f8

Observation f105ed3b-93ca-4826-b8d7-e8988352e9c9 · outbound

This paper cites an unresolved cited work.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:54.189749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:54.189749Z digest=sha256:b122c4ac3fe63bcdd159f537326541721b7a3e4db99ae59b7c7f8bdec7776f3c

Observation 7d9304c1-3dee-415d-92b3-b42649a97cf5 · outbound

This paper cites Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:54.253318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:54.253318Z digest=sha256:238be3ea73659ac4835c8f04b42570b75a34eb861f89a33bfc32dc29edb22ccb

Observation 60aa5429-51d5-4dd8-a379-f1250ea58b3f · outbound

This paper cites WhisperX: Time-Accurate Speech Transcription of Long-Form Audio.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition WhisperX: Time-Accurate Speech Transcription of Long-Form Audio

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:54.327892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:54.327892Z digest=sha256:cdf1e04d4c8ba2437c8a3452f80efbb63997edf763e10042980f75cafdcca028

Observation 6b018eb8-dd4f-450c-8ef0-256b36962a39 · outbound

This paper cites In: 2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: 2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:54.405095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:54.405095Z digest=sha256:9b67e0236f36616571b5e76f3c8cd307758cae53106f405ced47f668922f308f

Observation a873db63-7423-4755-a66c-75739bc9399d · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:54.567049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:54.567049Z digest=sha256:44a6be1e5e1498889b6acc4fe1acd738c0ff2060aab0ec3e525639e9c9e502b0

Observation c4d5d563-3613-49ad-aad0-996cf83555a0 · outbound

This paper cites Listen, Attend and Spell.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Listen, Attend and Spell

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:54.677464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:54.677464Z digest=sha256:38754961e4c47e325cd22a25b6eea2910c1f05ca19ea4c7a5cb73ba610e62079

Observation 8c35b0d7-c2cf-44c1-93b4-09c538a9986a · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Accelerating Large Language Model Decoding with Speculative Sampling

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:54.841372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:54.841372Z digest=sha256:2143adbc2a4aeee488150bec446857ca4cfb241eac7357def1b78d251ec42512

Observation 0a00891e-d3f5-4e73-b27d-8578017b231d · outbound

This paper cites FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:54.959703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:54.959703Z digest=sha256:201ed23c994c8c69f8018dd4552d7ceb0ad7c1527a9f776c2759b22151aed39c

Observation b914f1c1-138d-43ea-9bc0-1c88ea8f8d0b · outbound

This paper cites arXiv preprint arXiv:2511.00850 (2025).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition arXiv preprint arXiv:2511.00850 (2025)

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:55.143015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:55.143015Z digest=sha256:c64196c9ffb38e6daa5cc71e02517d83178ffee9c7500869d7a0a986f94bad5a

Observation 84590f14-97e8-4627-96c8-0976a52559ce · outbound

This paper cites AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:55.256063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:55.256063Z digest=sha256:01f2dabb885e8701d9d65566854cece4ea7b6c2e6c75c4c798032217af342c19

Observation 8a79d292-1f8a-4733-bdfd-72157ec3dde8 · outbound

This paper cites In: 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:55.344559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:55.344559Z digest=sha256:1d4e3cac019b37c074e097b6afbd4bc45e5aacabf8d04da3b0c8582298d9c900

Observation a699f2ed-2560-42c0-be04-d8e298569471 · outbound

This paper cites Better & Faster Large Language Models via Multi-token Prediction.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Better & Faster Large Language Models via Multi-token Prediction

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:55.501150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:55.501150Z digest=sha256:3a3f2b13e85a8b2349bb9f318194af3c7995887a52ac11b0fca0c43213ebf2c9

Observation 701c2852-13e5-40de-b600-afa692b17e6a · outbound

This paper cites In: Supervised sequence labelling with recurrent neural networks, pp.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: Supervised sequence labelling with recurrent neural networks, pp

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:55.684968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:55.684968Z digest=sha256:54f1569ba22330ced9f3562316c4a4422cacf46123bf97880fa31a81cd5bbc3c

Observation e98b20d4-e12e-451d-af7a-6cfb656d79e5 · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Sequence Transduction with Recurrent Neural Networks

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:55.806367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:55.806367Z digest=sha256:004c170c1556b04898b983bd4b977823bfe5be3c4cbaedb167b047409c1b5f07

Observation 2b3adb49-ff95-4ec7-a6e3-4ee3ce5b227e · outbound

This paper cites arXiv preprint arXiv:2602.10604 (2026).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition arXiv preprint arXiv:2602.10604 (2026)

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:55.896842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:55.896842Z digest=sha256:04e25a7aef21d43ed6127349346ba5e57ef5f4c6e06b136183662ac46c678c27

Observation 7fc80d42-bd14-4677-96a1-0555c731bc76 · outbound

This paper cites In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:55.951331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:55.951331Z digest=sha256:ebf604653be2b27e75a5ef7e195875328a2324d9d24ee424cb5bff852f9a6657

Observation 16ed9af0-bddf-4445-bedd-e80a5bb5dabd · outbound

This paper cites PMLR (2023).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition PMLR (2023)

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.028066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.028066Z digest=sha256:55244a7888315d5d01afc259a3f60349bd8bae6c8c10e6409579dd7fdef681fa

Observation a05dba3a-3f4d-45fe-ad13-fa4c033e29f2 · outbound

This paper cites StepAudio 2.5 Technical Report.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition StepAudio 2.5 Technical Report

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.110991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.110991Z digest=sha256:8f7d3f1ea3232ed168b93c239729fc94c47b77f32d9371aa669313458d7143a4

Observation fec2c2ba-554f-41c4-8d0b-b1181f731ba6 · outbound

This paper cites Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.212641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.212641Z digest=sha256:2f61c6daa512ab3742d4080e4f057a27bd00c82c5b593b053a7c8cf975b9920d

Observation e6ea5e0b-160c-4d36-be00-ea350751c1dd · outbound

This paper cites arXiv preprint arXiv:2509.24310 (2025).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition arXiv preprint arXiv:2509.24310 (2025)

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.287599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.287599Z digest=sha256:ef7ace2e6773d0323e2b111f9265ce4aad8afb8521ca98c2f346e5d984fc242d

Observation e9eafcfa-2543-4c00-8956-5556515a8dc7 · outbound

This paper cites Multimedia Tools and Applications80(6), 9411–9457 (2021).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Multimedia Tools and Applications80(6), 9411–9457 (2021)

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.371783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.371783Z digest=sha256:0b08cdb347a2b1229ed1f0a2626ed51dee4701741626cad2661db5c0a992d215

Observation 4294a865-6f85-425d-8e02-7c88ce2fa08b · outbound

This paper cites In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.439971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.439971Z digest=sha256:4cd9df8b0c8f8a215a107a9653075b5960a9cd8e2f0ff3cf26fd03ea3da15e60

Observation 670a9bb4-64f1-483b-8ea2-8f39f00f5179 · outbound

This paper cites In: Interspeech 2019.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: Interspeech 2019

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.559132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.559132Z digest=sha256:ee835fad30938ee5cecf033f73d9b31045fd65e872e7814dccfe343b2aece56f

Observation 85426615-17cb-45b6-863e-7499fc858af1 · outbound

This paper cites arXiv preprint arXiv:2601.18184 (2026).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition arXiv preprint arXiv:2601.18184 (2026)

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.661673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.661673Z digest=sha256:2bf380b6fcfe70daac4d7541f9bed2ad95c4ce7a627f8d2186e08aad8522ef70

Observation 34b7b98c-a437-43b3-9e85-a862db828b91 · outbound

This paper cites In: International conference on machine learning.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: International conference on machine learning

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.747587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.747587Z digest=sha256:dd0bf3387b33827a3577f66d21bdc561eb9c884e8dc259732978cc62eed3fe2b

Observation 49398783-16d2-4f38-8552-36d00e3cdcfd · outbound

This paper cites Qwen3-ASR Technical Report.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Qwen3-ASR Technical Report

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.837223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.837223Z digest=sha256:5077e8b818708f9ea768f615b642064b8b29b16b2213cc4c96d9c488ad86f95f

Observation 96b7d5c6-40bd-4372-b052-9a4518c7b4ba · outbound

This paper cites arXiv preprint arXiv:2511.15848 (2025).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition arXiv preprint arXiv:2511.15848 (2025)

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:56.948109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:56.948109Z digest=sha256:3e7a9b5ca835c8c5cf255bfe2903d928a987e48456627d652977981c339e90a8

Observation fb3eaa16-e7e1-43db-a0ca-c7e1b0191f4c · outbound

This paper cites Step-Audio 2 Technical Report.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Step-Audio 2 Technical Report

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.074975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.074975Z digest=sha256:e72f10c469564c1b014427c06b2f4c91456e99ec00424cba77461c2404967d30

Observation f65dfae5-4eca-46bc-98c1-0ede1ccce1c9 · outbound

This paper cites Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.190594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.190594Z digest=sha256:0edc7129780e57910d505f4f6056ebbba26d32ba0f58976355c2dcacc3f9cd9c

Observation e66aebf7-654d-4632-9ae6-b30d514d25ac · outbound

This paper cites Qwen3-Omni Technical Report.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Qwen3-Omni Technical Report

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.308232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.308232Z digest=sha256:edc0570f23dd27eca582fd137c16f8eeb334f0457c584b9a9e10c1f5ed8303cc

Observation 41173a3e-492f-4ecf-8dd3-bf59f3429dba · outbound

This paper cites In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.421541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.421541Z digest=sha256:ba43136e13dfba8ddd5c0c25f4e308cb1d1cb0b9bc3a43e6b0f18e3528782c3c

Observation c37169ab-571b-462d-9532-9e62f73f0700 · outbound

This paper cites In: Proc.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: Proc

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.509325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.509325Z digest=sha256:939ca63d214b7c1fde1486e495a348c53d006abd90334c14d0d2bf0ad080aca0

Observation 68e690a5-c5a6-4dc7-9bad-08c34e9a21f5 · outbound

This paper cites In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.569911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.569911Z digest=sha256:085396eac749e3c8f93dde3b906902eafef59f389d89a2b0398f56611767bcbb

Observation e5a96d3b-4301-4639-8848-e9d03eedb21f · outbound

This paper cites DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.633052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.633052Z digest=sha256:41af5c259c2662c31ed473e725a5659554c7fadb67b075cccee391818f407849

Observation d6e5ce31-033b-4fde-86cd-ac72e05ad0a5 · outbound

This paper cites Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.724078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.724078Z digest=sha256:e5c2bbe67d1f7406a27fe27fb21a318e47f9f7cecb166a00bc15ae29bd4d2c92

Observation 92418081-62ad-4080-9924-bd5911203b0b · outbound

This paper cites The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.787394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.787394Z digest=sha256:a04e5fce1817be1df7a3449a807fc8462564298e6dcab06db526b216f3b09b54

Observation 3b207db3-9e4f-48f1-b3d8-f17750f315d2 · outbound

This paper cites IEEE Transactions on Audio, Speech and Language Processing (2025).

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition IEEE Transactions on Audio, Speech and Language Processing (2025)

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.856488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.856488Z digest=sha256:c85b54d327d17f4c3c78c8a12900abeb1055515861bff63379368cbdf83ae115

Observation cad70a16-691f-4939-ab2e-c04847e2c8b7 · outbound

This paper cites Step-Audio-R1.5 Technical Report.

ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognition Step-Audio-R1.5 Technical Report

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-03T10:13:57.954776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T10:13:57.954776Z digest=sha256:03f61c2dd34ec58dd3f1aa411a5479c32516fe504e97a0b47037c3cc868a762c

Pith citing papers

No inbound Pith citation observations are available.