Paper Citation Record · LEDGER

LL-SDR: Low-Latency Speech enhancement through Discrete Representations

As of 5 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 1 inbound Pith citation observation for arXiv:2603.20242.

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

pith.paper-citation-record.v1
2603.20242 v2

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T18:32:55.502748Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T18:32:52.575593Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d2e7fe4a-0c47-4f82-b465-8151c3e8cbeb · outbound

This paper cites Most existing speech enhancement approaches are built upon continuous acoustic features.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Most existing speech enhancement approaches are built upon continuous acoustic features

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:52.463546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9fa0a0c-834c-4aec-8b38-e42e3c54cfad · outbound

This paper cites LL-SDR: Low-Latency Speech enhancement through Discrete Representations.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations LL-SDR: Low-Latency Speech enhancement through Discrete Representations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:52.575593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f30f18fd-fb72-49b0-ad40-1a465844a4f8 · outbound

This paper cites Dataset For the ablation study, we train our model on LibriSpeech- 100 [24] and the DNS Challenge [25] datasets.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Dataset For the ablation study, we train our model on LibriSpeech- 100 [24] and the DNS Challenge [25] datasets

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:52.649190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 013c52e9-ba7e-4923-8f79-d21fdc0da75a · outbound

This paper cites an unresolved cited work.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:52.730331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8903de41-ba06-460b-b111-11df822cbdd9 · outbound

This paper cites Generative AI tools were used solely for minor editing and language polishing to improve clarity and fluency of the manuscript.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Generative AI tools were used solely for minor editing and language polishing to improve clarity and fluency of the manuscript

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:52.795857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 568c613b-e3ec-4815-9a83-4528e52001d3 · outbound

This paper cites FRCRN: Boosting feature representation using frequency recurrence for monaural speech enhancement,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations FRCRN: Boosting feature representation using frequency recurrence for monaural speech enhancement,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:52.932240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a89b78c2-ea07-4f96-b021-6f991e753046 · outbound

This paper cites Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:53.023853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2b68bf5-0169-49f2-a737-85e9b8c42fa4 · outbound

This paper cites Conv-TasNet: Surpassing ideal time–frequency magnitude masking for speech separation,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Conv-TasNet: Surpassing ideal time–frequency magnitude masking for speech separation,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:53.084071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f004800a-4f96-4a74-b53a-36715413a35c · outbound

This paper cites Genhancer: High-fidelity speech enhancement via generative modeling on discrete codec tokens,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Genhancer: High-fidelity speech enhancement via generative modeling on discrete codec tokens,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:53.238264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2662ee89-d2f3-499f-a677-89c67b4e8139 · outbound

This paper cites SELM: Speech enhancement using discrete tokens and language models,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations SELM: Speech enhancement using discrete tokens and language models,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:53.356399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c090c6-eef2-4dcf-b554-3be923f244d6 · outbound

This paper cites LLaSE-g1: In- centivizing generalization capability for LLaMA-based speech enhancement,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations LLaSE-g1: In- centivizing generalization capability for LLaMA-based speech enhancement,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:53.454516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0da8715-8ef0-4aa0-93cd-09a81aee519e · outbound

This paper cites GenSE: Generative speech enhancement via language models using hi- erarchical modeling,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations GenSE: Generative speech enhancement via language models using hi- erarchical modeling,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:53.581834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74a783ad-1605-421e-9244-0b0e9cab35c9 · outbound

This paper cites An EM approach to non-autoregressive conditional sequence generation,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations An EM approach to non-autoregressive conditional sequence generation,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:53.698147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2db1893b-2578-4b2c-8713-455d89d8a8cb · outbound

This paper cites Real time speech en- hancement in the waveform domain,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Real time speech en- hancement in the waveform domain,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:53.827187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc46cd87-2708-499a-9b48-3395090dc840 · outbound

This paper cites A scalable noisy speech dataset and online subjective test framework,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations A scalable noisy speech dataset and online subjective test framework,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:53.966077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc1a5caf-fcc9-4544-9afd-7a55265ccb1b · outbound

This paper cites An individualized super-Gaussian single microphone speech enhancement for hearing aid users with smart- phone as an assistive device,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations An individualized super-Gaussian single microphone speech enhancement for hearing aid users with smart- phone as an assistive device,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.044327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8273f10-2711-4575-9569-23bd46d3e489 · outbound

This paper cites An investigation into the effectiveness of enhancement in ASR training and test for Chime-5 dinner party transcription,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations An investigation into the effectiveness of enhancement in ASR training and test for Chime-5 dinner party transcription,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.117621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6aa3bfe-a0a9-498d-ada0-7e7a9aa1ca6a · outbound

This paper cites Speech enhancement using continuous embeddings of neural audio codec,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Speech enhancement using continuous embeddings of neural audio codec,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.174262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db4bb73c-2a28-4538-8da5-5b83c4e9c869 · outbound

This paper cites SoundStream: An end-to-end neural audio codec,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations SoundStream: An end-to-end neural audio codec,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.214550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d585135-46e6-477f-ada0-1ecec105eacb · outbound

This paper cites Anytime sampling for autoregressive models via ordered autoen- coding,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Anytime sampling for autoregressive models via ordered autoen- coding,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.276206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f57ee777-0273-4c12-8795-74133add4ae0 · outbound

This paper cites Learning ordered repre- sentations with nested dropout,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Learning ordered repre- sentations with nested dropout,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.319788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12eeee71-9c62-4c42-9965-9486aa1ac5eb · outbound

This paper cites SoCodec: A semantic-ordered multi-stream speech codec for ef- ficient language model based text-to-speech synthesis,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations SoCodec: A semantic-ordered multi-stream speech codec for ef- ficient language model based text-to-speech synthesis,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.372884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b44a23d4-fce1-4287-8e3e-6e118337959c · outbound

This paper cites HuBERT: How much can a bad teacher benefit ASR pre-training?.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations HuBERT: How much can a bad teacher benefit ASR pre-training?

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.425947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c3498ab-f83c-4229-b9f9-7e74cb535337 · outbound

This paper cites SpeechTok- enizer: Unified speech tokenizer for speech language models,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations SpeechTok- enizer: Unified speech tokenizer for speech language models,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.483921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e6fefad-3f24-4ca7-9f90-3ec5ec2511d4 · outbound

This paper cites InfoNCE: Identifying the gap between theory and practice,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations InfoNCE: Identifying the gap between theory and practice,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.558107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82b30a6a-8aad-4ed5-b94f-fdc2b950abec · outbound

This paper cites Revisiting over- smoothness in text to speech,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Revisiting over- smoothness in text to speech,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.614777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 116650b9-ddbf-4ae4-9261-d16a6f31153c · outbound

This paper cites Noise contrastive estimation and negative sampling for conditional models: Consistency and statistical effi- ciency,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Noise contrastive estimation and negative sampling for conditional models: Consistency and statistical effi- ciency,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.666850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2231314a-56fc-4134-a29b-98dabccd397e · outbound

This paper cites High-fidelity audio compression with improved RVQGAN,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations High-fidelity audio compression with improved RVQGAN,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.747139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bdaa66d-c737-4b9f-a398-619cfa7c3c34 · outbound

This paper cites Librispeech: An ASR corpus based on public domain audio books,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Librispeech: An ASR corpus based on public domain audio books,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.806272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84156fc7-4d6f-4c01-ad3e-ffc80e1e7a34 · outbound

This paper cites The Interspeech 2020 deep noise suppression challenge: Datasets, sub- jective testing framework, and challenge results,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations The Interspeech 2020 deep noise suppression challenge: Datasets, sub- jective testing framework, and challenge results,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.861368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b43a43b2-2e0c-4106-a87a-e2b4ef198470 · outbound

This paper cites The diverse environments multi-channel acoustic noise database (DEMAND): A database of multichannel environmental noise recordings,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations The diverse environments multi-channel acoustic noise database (DEMAND): A database of multichannel environmental noise recordings,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.919935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93cbb30b-dfa0-47f9-a841-1a996217195a · outbound

This paper cites DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise sup- pressors,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise sup- pressors,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:54.957394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 886afcba-ff86-4bca-8fc4-358ee0b077db · outbound

This paper cites Focal- Codec: Low-bitrate speech coding via focal modulation networks,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations Focal- Codec: Low-bitrate speech coding via focal modulation networks,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:55.035794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 721a9ff0-5ec5-4e34-b8ff-954798d43b2e · outbound

This paper cites FocalCodec- Stream: Streaming low-bitrate speech coding via causal distilla- tion,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations FocalCodec- Stream: Streaming low-bitrate speech coding via causal distilla- tion,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:55.184410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 931c142b-e3cf-43b5-aa00-8449fcf9e3a4 · outbound

This paper cites MaskSR: Masked language model for full-band speech restoration,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations MaskSR: Masked language model for full-band speech restoration,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:55.328549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8d032c0-be0f-40fb-944f-0adf82f126e3 · outbound

This paper cites AnyEnhance: A unified generative model with prompt- guidance and self-critic for voice enhancement,.

LL-SDR: Low-Latency Speech enhancement through Discrete Representations AnyEnhance: A unified generative model with prompt- guidance and self-critic for voice enhancement,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T18:32:55.502748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f9fa0a0c-834c-4aec-8b38-e42e3c54cfad · inbound