Paper Citation Record · LEDGER

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation

As of 8 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 4 inbound Pith citation observations for arXiv:2505.19774.

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

pith.paper-citation-record.v1
2505.19774 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:12:49.357205Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:12:46.355892Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T16:28:39.508010Z

Reference resolution

39 of 39 outbound references displayed

verified exact3
verified fuzzy11
unresolved21
parse uncertain0
malformed identifier3
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5f25726a-38b9-46a3-aa95-c855e7e20be6 · outbound

This paper cites Full-context encoders [1, 2], leveraging entire speech utterances, offer superior accuracy but higher latency, making them ideal for offline use.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Full-context encoders [1, 2], leveraging entire speech utterances, offer superior accuracy but higher latency, making them ideal for offline use

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:53.104993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9e950d8d-1520-491e-aa3a-3cb394e00e08 · outbound

This paper cites DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:46.355892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6ad7272-62b5-4be4-9a9a-02d1a43c21e6 · outbound

This paper cites an unresolved cited work.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:52.685483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fa9dcbb8-7061-43e1-b826-bdaec77172bb · outbound

This paper cites Results Table 1 presents a comparative analysis of the dual-mode en- coder and single-mode baseline encoders across full-context and streaming scenarios, in ASR tasks.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Results Table 1 presents a comparative analysis of the dual-mode en- coder and single-mode baseline encoders across full-context and streaming scenarios, in ASR tasks

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:12:52.286979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 46293429-1243-40a3-9b44-805d29587b3a · outbound

This paper cites Due to these variations, absolute WERs reported after our SUPERB bench- marking are higher than those reported in the original works.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Due to these variations, absolute WERs reported after our SUPERB bench- marking are higher than those reported in the original works

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:52.496675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2f177c02-655e-4476-ab67-569e5eed50a5 · outbound

This paper cites an unresolved cited work.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:52.908471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c65c6e3a-f562-467d-81ce-1e2a83a8e978 · outbound

This paper cites Results Table 4 compares the performance of the DuRep-2B encoder in two inference modes with open-source encoders on ASR and non-ASR tasks, evaluated using SUPERB framework (3.4).

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Results Table 4 compares the performance of the DuRep-2B encoder in two inference modes with open-source encoders on ASR and non-ASR tasks, evaluated using SUPERB framework (3.4)

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:52.127133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ff259256-d9db-4d11-929e-1baa37b58f5e · outbound

This paper cites In ASR-SUPERB evaluations, on average, the DuRep-200M encoder outperforms baselines by 13.06% in streaming and 10.42% in non-streaming mode.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation In ASR-SUPERB evaluations, on average, the DuRep-200M encoder outperforms baselines by 13.06% in streaming and 10.42% in non-streaming mode

Reference 8

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:12:51.897019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3df5a67f-bfa2-4c30-b26b-c66d3e4dc616 · outbound

This paper cites an unresolved cited work.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:51.660143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c9700196-b019-4ea0-b376-8035a5b3ad6b · outbound

This paper cites Google usm: Scaling automatic speech recognition beyond 100 languages,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Google usm: Scaling automatic speech recognition beyond 100 languages,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:46.963664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec2afa29-f28f-4268-8c15-77ae428a0d6f · outbound

This paper cites Self-supervised speech representation learning: A review,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Self-supervised speech representation learning: A review,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:48.108528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac4fef8f-9040-40f2-8b58-b96e78ba18bf · outbound

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

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Robust Speech Recognition via Large-Scale Weak Supervision

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:47.158251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b8ab252-ca3f-4248-ad46-fc0a3ba2ac4a · outbound

This paper cites Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:47.243261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81e526fa-4163-487f-9b74-bf211c4000bb · outbound

This paper cites Conformer with dual-mode chunked attention for joint online and offline ASR.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Conformer with dual-mode chunked attention for joint online and offline ASR

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:12:50.153372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4aebe4a4-8b17-490a-ae73-0d5d352b39a3 · outbound

This paper cites Multi- mode transformer transducer with stochastic future context,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Multi- mode transformer transducer with stochastic future context,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:51.451479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5b58ca95-c45e-4e83-8170-4a4517a1083b · outbound

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

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Fleurs: Few-shot learning evaluation of universal representations of speech,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:51.072372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9acf3d35-c4ac-457a-8387-83306a72b0c6 · outbound

This paper cites Variable Attention Masking for Configurable Transformer Transducer Speech Recognition.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Variable Attention Masking for Configurable Transformer Transducer Speech Recognition

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:12:49.920805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 862a48ce-cd21-4cf8-9386-2c06d30700c2 · outbound

This paper cites Sequence transduction with recurrent neural networks,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Sequence transduction with recurrent neural networks,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:51.319686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c822dc6b-1ea6-4b31-a86a-eea374679c94 · outbound

This paper cites SUPERB: Speech processing Universal PERformance Benchmark.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation SUPERB: Speech processing Universal PERformance Benchmark

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:47.829556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 534ac630-f760-4521-9d3a-06d5baefddae · outbound

This paper cites Self-supervised Learning with Random-projection Quantizer for Speech Recognition.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Self-supervised Learning with Random-projection Quantizer for Speech Recognition

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:12:49.761320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 157c9368-a37c-426c-ae3f-e7a5d50f0181 · outbound

This paper cites Universal-1: Robust and accurate multi- lingual speech-to-text,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Universal-1: Robust and accurate multi- lingual speech-to-text,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:51.197138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b7da4468-3076-44dc-a9eb-cc06b1140fcc · outbound

This paper cites ML-SUPERB: Multilingual Speech Universal PERformance Benchmark.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation ML-SUPERB: Multilingual Speech Universal PERformance Benchmark

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:49.072445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a09b4471-d3be-4e13-9274-7b338103663e · outbound

This paper cites Lib- rispeech: An asr corpus based on public domain audio books,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Lib- rispeech: An asr corpus based on public domain audio books,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:48.177512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cca1858-305a-43de-a932-0019aa2902fb · outbound

This paper cites Mls: A large-scale multilingual dataset for speech research,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Mls: A large-scale multilingual dataset for speech research,

Reference 24

Resolution: malformed identifier; no resolver link, observed 2026-08-07T14:12:48.292894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8907619b-305c-480c-bbdf-d9ac1a0a2de7 · outbound

This paper cites Common Voice: A Massively-Multilingual Speech Corpus.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Common Voice: A Massively-Multilingual Speech Corpus

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:48.384304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52b343b8-f89f-43d4-9dfa-e35a1fa2c00c · outbound

This paper cites The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:48.463964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02ec53c7-2e9d-4eb7-ba40-45b105b4b1a3 · outbound

This paper cites On the utility of self-supervised mod- els for prosody-related tasks,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation On the utility of self-supervised mod- els for prosody-related tasks,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:50.352190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fc9a8ab5-343b-4ba1-ae6c-dedcb0b7b62b · outbound

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

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:48.668479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c545bf0-d54b-4e6d-a7c6-dcd66f3bcc2b · outbound

This paper cites free public domain audiobooks,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation free public domain audiobooks,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:50.931336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3dc4be5b-c3cf-4eb8-bb71-2b8f6cede795 · outbound

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

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Conformer: Convolution-augmented transformer for speech recognition,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:48.785451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91fb33ab-6728-4d4c-9828-3681a6d691d6 · outbound

This paper cites Long short-term memory,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Long short-term memory,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:48.979925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4abe35ea-4d8e-4cca-845f-33de1adffd47 · outbound

This paper cites Specaugment: A simple data augmentation method for automatic speech recognition,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Specaugment: A simple data augmentation method for automatic speech recognition,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:50.723614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4690a66b-005f-4d52-9384-106eafc4bcdc · outbound

This paper cites Msp-podcast corpus: A large naturalistic speech emotional dataset,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Msp-podcast corpus: A large naturalistic speech emotional dataset,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:50.534911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 98f3f17c-256a-433b-8ca4-77f34dc87fbf · outbound

This paper cites wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:49.162149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a313904-5856-45fa-90f8-15d6b4658691 · outbound

This paper cites mHuBERT-147: A Compact Multilingual HuBERT Model.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation mHuBERT-147: A Compact Multilingual HuBERT Model

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:49.231627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2af490b-06d7-4ba1-83c2-e87bfd0522b4 · outbound

This paper cites Wavlm: Large-scale self-supervised pre-training for full stack speech processing,.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Wavlm: Large-scale self-supervised pre-training for full stack speech processing,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:49.296912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e9dd8c2-89ec-41fb-9003-a684f8c85455 · outbound

This paper cites Conformer: Convolution-augmented Transformer for Speech Recognition.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Conformer: Convolution-augmented Transformer for Speech Recognition

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:48.881846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95b117fd-89c3-4d1b-b4e6-a7450b5d471a · outbound

This paper cites Multi-mode Transformer Transducer with Stochastic Future Context.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Multi-mode Transformer Transducer with Stochastic Future Context

Reference 2021

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T14:12:50.045674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a5185df-5743-4224-b270-77f4de0e01cf · outbound

This paper cites Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages.

DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:47.058460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9e950d8d-1520-491e-aa3a-3cb394e00e08 · inbound