Paper Citation Record · LEDGER

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network

As of 21 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 2 inbound Pith citation observations for arXiv:2505.18533.

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

pith.paper-citation-record.v1
2505.18533 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:33:17.541033Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:33:17.039337Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T17:16:21.326225Z

Reference resolution

36 of 36 outbound references displayed

verified exact1
verified fuzzy29
unresolved5
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3b171358-adda-4a28-80d8-4cf8fd3f7ed6 · outbound

This paper cites TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:33:17.039337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3c9e994-654d-4ca2-847a-35bfa40ac99d · outbound

This paper cites 1, our proposed framework is composed of three parts: filling, separation, and restoration stages.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network 1, our proposed framework is composed of three parts: filling, separation, and restoration stages

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:19.040102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ebee51b1-55e8-4a13-983c-cbfcd707c20f · outbound

This paper cites Datasets We use the data provided in Track 1 of the Interspeech 2025 URGENT Challenge and employ the official scripts 5 for simu- lation.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Datasets We use the data provided in Track 1 of the Interspeech 2025 URGENT Challenge and employ the official scripts 5 for simu- lation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.949618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2d4eabc1-1ba3-4a00-8da4-757d5b67010c · outbound

This paper cites 6https://urgent-challenge.github.io/ urgent2025/rules/ Table 3: Results of the ablation study on the official validation set.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network 6https://urgent-challenge.github.io/ urgent2025/rules/ Table 3: Results of the ablation study on the official validation set

Reference 4

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:33:18.920372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2a154d93-d178-4a9a-b98a-0a3485712308 · outbound

This paper cites We introduce a three-stage framework capa- ble of handling input speech with different distortions and sam- pling frequencies.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network We introduce a three-stage framework capa- ble of handling input speech with different distortions and sam- pling frequencies

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.881212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 129b96b6-aff5-449e-813a-eec84a354441 · outbound

This paper cites 12274221) and the Yangtze River Delta Science and Technology Innovation Community Joint Re- search Project (Grant No.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network 12274221) and the Yangtze River Delta Science and Technology Innovation Community Joint Re- search Project (Grant No

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.843714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b0c29a65-9d3f-4b48-a4e1-a6a292178c62 · outbound

This paper cites Audio codec enhancement with genera- tive adversarial networks,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Audio codec enhancement with genera- tive adversarial networks,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.619814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 082563e9-35d5-44b5-be4f-d490c86fb641 · outbound

This paper cites Icassp 2023 speech signal improvement challenge,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Icassp 2023 speech signal improvement challenge,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.791232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 82cfbf0b-2147-4aea-b449-116954c86aac · outbound

This paper cites Icassp 2024 speech signal improvement challenge,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Icassp 2024 speech signal improvement challenge,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.744895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9190733c-cf0d-4a33-b1bd-4e4404ed4028 · outbound

This paper cites To- ward universal speech enhancement for diverse input conditions,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network To- ward universal speech enhancement for diverse input conditions,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.710161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bef097dd-1297-4b7c-b4c4-2807dc63adaa · outbound

This paper cites Toward universal speech enhancement for diverse input conditions,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Toward universal speech enhancement for diverse input conditions,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.673898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 67e52e2c-c251-41b0-b8cc-e6e59033739e · outbound

This paper cites Declipping speech using deep filter- ing,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Declipping speech using deep filter- ing,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.643062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bf5c9c37-9ad2-43bb-adff-66a0275f93fc · outbound

This paper cites Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:33:17.708214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 37ac80f0-1a12-44c8-8482-069996b1c6ae · outbound

This paper cites Ks-net: Multi-band joint speech restoration and enhancement network for 2024 icassp ssi chal- lenge,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Ks-net: Multi-band joint speech restoration and enhancement network for 2024 icassp ssi chal- lenge,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.378780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3e299208-62eb-40c2-bc46-29fa1d519ae3 · outbound

This paper cites Bs- plcnet: Band-split packet loss concealment network with multi- task learning framework and multi-discriminators,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Bs- plcnet: Band-split packet loss concealment network with multi- task learning framework and multi-discriminators,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.572937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 931ed788-842f-4bfb-aeeb-d082e6392a10 · outbound

This paper cites V oicefixer: A unified framework for high-fidelity speech restoration,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network V oicefixer: A unified framework for high-fidelity speech restoration,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.538558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f0976774-6a0a-452c-9d3e-79d70ba0edff · outbound

This paper cites Decoupling magnitude and phase estimation with deep resunet for music source separation,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Decoupling magnitude and phase estimation with deep resunet for music source separation,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.500994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 237e5506-f7f2-4076-a973-86b9ff9c9270 · outbound

This paper cites Universal Speech Enhancement with Score-based Diffusion.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Universal Speech Enhancement with Score-based Diffusion

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:33:17.320282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99bca700-78fb-4614-9eff-945e5f441ebe · outbound

This paper cites We employ the same training loss as in Gesper [13], consisting of reconstruction, adversarial, and feature-matching terms, with respective weights of 20, 1, and 1.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network We employ the same training loss as in Gesper [13], consisting of reconstruction, adversarial, and feature-matching terms, with respective weights of 20, 1, and 1

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:19.000149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1a7380cd-b9e5-4509-8683-841a54a58888 · outbound

This paper cites Cascaded time + time-frequency unet for speech enhancement: Jointly addressing clipping, codec distortions, and gaps,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Cascaded time + time-frequency unet for speech enhancement: Jointly addressing clipping, codec distortions, and gaps,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.463131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 33222f69-496a-4873-931e-eaf78159d56a · outbound

This paper cites Gesper: A unified framework for gen- eral speech restoration,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Gesper: A unified framework for gen- eral speech restoration,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.427121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b3d678bd-8156-4132-9306-62a65ee7dd9e · outbound

This paper cites Rad-net: A repairing and denoising network for speech signal improvement,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Rad-net: A repairing and denoising network for speech signal improvement,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.333944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 47b90516-f869-4929-800d-8dd0305b3c59 · outbound

This paper cites General speech restoration using two-stage generative adversarial networks,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network General speech restoration using two-stage generative adversarial networks,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.286734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation da74cabf-7a6b-4d11-9c6c-150c6d06c317 · outbound

This paper cites Tf-gridnet: Integrating full-and sub-band modeling for speech separation,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Tf-gridnet: Integrating full-and sub-band modeling for speech separation,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.255967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7ea7b61d-8e61-470d-bd8a-b744a5ad04b5 · outbound

This paper cites Channel-wise subband input for better voice and accompaniment separation on high resolution music,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Channel-wise subband input for better voice and accompaniment separation on high resolution music,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.231715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ec5750a9-616c-41b6-9b32-8f2afa15c630 · outbound

This paper cites Bigv- gan: A universal neural vocoder with large-scale training,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Bigv- gan: A universal neural vocoder with large-scale training,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.194224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 48427ff3-bf3e-40f8-a8d8-626955b01dd1 · outbound

This paper cites Mel-cepstral distance measure for objective speech quality assessment,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Mel-cepstral distance measure for objective speech quality assessment,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.167155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 807cc2a9-6958-4994-a669-e12b8f951fa0 · outbound

This paper cites Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality as- sessment of narrow-band telephone networks and speech codecs,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality as- sessment of narrow-band telephone networks and speech codecs,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.097818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5a3a1b19-0670-4b66-9838-141b0bcb2600 · outbound

This paper cites Dnsmos P.835: A non- intrusive perceptual objective speech quality metric to evaluate noise suppressors,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Dnsmos P.835: A non- intrusive perceptual objective speech quality metric to evaluate noise suppressors,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.052321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a6f37b9d-21cb-4d5c-bd28-5be256cecd58 · outbound

This paper cites UTMOS: utokyo-sarulab system for voicemos challenge 2022,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network UTMOS: utokyo-sarulab system for voicemos challenge 2022,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:18.005931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fc8fe183-8512-4037-ae2d-ebc067a34165 · outbound

This paper cites Evaluation metrics for generative speech en- hancement methods: Issues and perspectives,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Evaluation metrics for generative speech en- hancement methods: Issues and perspectives,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:17.972738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 842b9bfb-cf83-425b-a98c-4ac58597faec · outbound

This paper cites Speechbertscore: Reference-aware automatic evaluation of speech generation leveraging nlp evaluation metrics,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Speechbertscore: Reference-aware automatic evaluation of speech generation leveraging nlp evaluation metrics,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:17.913769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7a107416-b047-4253-9208-4b4864329d07 · outbound

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

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Wavlm: Large-scale self- supervised pre-training for full stack speech processing,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:33:17.494906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0ce569d-81fb-44b5-a73e-50f772beec46 · outbound

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

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Speechtok- enizer: Unified speech tokenizer for speech language models,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:33:17.508050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a50516e-a3c9-4b24-9ea2-08d2ff8c88f1 · outbound

This paper cites An algorithm for predicting the in- telligibility of speech masked by modulated noise maskers,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network An algorithm for predicting the in- telligibility of speech masked by modulated noise maskers,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:33:17.535427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa54130d-7789-4910-8abf-22b9fdd4a2d8 · outbound

This paper cites Perceptual objective listening quality assessment (polqa), the third generation itu-t standard for end-to-end speech quality measurement part i—temporal align- ment,.

TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Perceptual objective listening quality assessment (polqa), the third generation itu-t standard for end-to-end speech quality measurement part i—temporal align- ment,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:33:17.787235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 3b171358-adda-4a28-80d8-4cf8fd3f7ed6 · inbound