Paper Citation Record · LEDGER

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge

As of 7 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 1 inbound Pith citation observation for arXiv:2506.00809.

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

pith.paper-citation-record.v1
2506.00809 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:01:34.417494Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:01:31.923229Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T12:01:34.538061Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy16
unresolved18
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f96e1558-c09a-4ec9-bc1f-297b2ddd8eed · outbound

This paper cites an unresolved cited work.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:01:38.174821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bb16165a-f05c-4d15-a8f1-15c85410c3ea · outbound

This paper cites FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:01:34.589250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e2a4906f-7f91-4ca1-bf5c-16867dba7ac7 · outbound

This paper cites an unresolved cited work.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Unresolved cited work

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T12:01:37.996812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0f26afc9-d691-42b6-9327-7378c8c4bf05 · outbound

This paper cites an unresolved cited work.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:01:37.838598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ae84b20e-900d-4433-a01e-92e7fc197dc5 · outbound

This paper cites an unresolved cited work.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:01:37.686806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 493b2714-f97c-4ee9-b979-994b2451c8dc · outbound

This paper cites an unresolved cited work.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:01:37.479628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 367a6ba7-5dc3-45ec-8632-5163a3d54fde · outbound

This paper cites Interspeech 2025 URGENT speech enhancement challenge,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Interspeech 2025 URGENT speech enhancement challenge,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:37.321324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e5d716a5-6494-4ba8-8764-96a617dcba7d · outbound

This paper cites Music source separation in the waveform domain,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Music source separation in the waveform domain,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:37.157527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9236ba3f-ca3a-457c-87bf-2b3d0d6f8ccd · outbound

This paper cites Scnet: Sparse compression network for music source separation,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Scnet: Sparse compression network for music source separation,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:32.457123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b56dc0e3-8825-4e22-9c8e-a5f8ab94ea99 · outbound

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

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Tf-gridnet: Integrating full-and sub-band modeling for speech separation,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:36.988000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d61be144-a88a-4633-b3e7-d89311cd736c · outbound

This paper cites Speech enhancement and dereverberation with diffusion-based generative models,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Speech enhancement and dereverberation with diffusion-based generative models,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:36.807544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7f30d897-1930-4cd6-8288-40e72fa14510 · outbound

This paper cites Storm: A diffusion-based stochastic regeneration model for speech en- hancement and dereverberation,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Storm: A diffusion-based stochastic regeneration model for speech en- hancement and dereverberation,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:32.624736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3084c8b7-68a5-4aa8-af85-ef8162c234d3 · outbound

This paper cites Hifi-gan-2: Studio-quality speech enhancement via generative adversarial networks condi- tioned on acoustic features,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Hifi-gan-2: Studio-quality speech enhancement via generative adversarial networks condi- tioned on acoustic features,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:36.658011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a54bcdaa-fceb-45ee-8f8e-6f57bd4c5de5 · outbound

This paper cites Finally: fast and universal speech enhancement with studio-like quality,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Finally: fast and universal speech enhancement with studio-like quality,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:32.799443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d81cf185-7287-4262-b83a-8275e23b2f9e · outbound

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

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Genhancer: High-fidelity speech enhancement via generative modeling on discrete codec tokens,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:36.511150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c33007a3-d314-46da-8999-29a71cdf94d1 · outbound

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

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge High-fidelity audio compression with improved rvqgan,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:32.970893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde14055-1360-4136-b039-9d86cbc862d0 · outbound

This paper cites High fidelity neural audio compression,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge High fidelity neural audio compression,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:36.322726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation be01b860-3c63-4c64-8bdc-5f7424d1977c · outbound

This paper cites SoundStorm: Efficient Parallel Audio Generation.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge SoundStorm: Efficient Parallel Audio Generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:33.109033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19f0fa93-94d0-427f-9b34-cbae6b8e646d · outbound

This paper cites EDM-TTS: Efficient Dual-Stage Masked Modeling for Alignment-Free Text-to- Speech Synthesis,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge EDM-TTS: Efficient Dual-Stage Masked Modeling for Alignment-Free Text-to- Speech Synthesis,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:36.166253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ab169d63-ea66-4383-9107-a12ba84be74b · outbound

This paper cites Towards robust speech representation learning for thousands of languages,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Towards robust speech representation learning for thousands of languages,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:35.993984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation daccfddc-1153-4d64-8615-c12806cf20ba · outbound

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

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Wavlm: Large-scale self- supervised pre-training for full stack speech processing,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:33.340225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98eba353-9f50-4105-b90f-ba965fc01bae · outbound

This paper cites Tokensplit: Using dis- crete speech representations for direct, refined, and transcript- conditioned speech separation and recognition,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Tokensplit: Using dis- crete speech representations for direct, refined, and transcript- conditioned speech separation and recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:35.799869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ce297c90-ccf8-46eb-ac67-7aac19c9494a · outbound

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

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Conformer: Convolution-augmented transformer for speech recognition,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:33.460059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae059441-79d8-4879-ba5a-4091d8320f97 · outbound

This paper cites Improving music source separation based on deep neural networks through data augmentation and network blending,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Improving music source separation based on deep neural networks through data augmentation and network blending,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:35.643525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6bd82b1a-d667-435f-b466-6106e1fafe35 · outbound

This paper cites Sdr– half-baked or well done?.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Sdr– half-baked or well done?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:33.621229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 478ab6df-37d6-407f-a199-7e20b7016ef7 · outbound

This paper cites Simple and Effective Zero-shot Cross-lingual Phoneme Recognition.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Simple and Effective Zero-shot Cross-lingual Phoneme Recognition

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:33.692653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f654e45-7586-4867-98ef-7d2b7fc57871 · outbound

This paper cites Utmos: Utokyo-sarulab system for voicemos challenge 2022,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Utmos: Utokyo-sarulab system for voicemos challenge 2022,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:35.442379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9be281a7-9a0f-4479-9893-c94351461137 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Adam: A Method for Stochastic Optimization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:33.840130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf70be28-8521-4d58-b70f-47f04c9363d0 · outbound

This paper cites Simulating wind noise with airflow speed-dependent characteristics,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Simulating wind noise with airflow speed-dependent characteristics,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:35.295694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d570bedd-2bab-4dc0-908a-c3613b9899ec · 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,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge 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 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:35.127198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ed435efb-429a-419e-b04b-a605f6b7000a · outbound

This paper cites Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:34.000498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 565395df-ba1f-40ff-97d4-ec376514dffa · outbound

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

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge An algorithm for predicting the in- telligibility of speech masked by modulated noise maskers,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:34.090779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c782e164-6f7b-4002-92f4-6293e93cf082 · outbound

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

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Mel-cepstral distance measure for objective speech quality assessment,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:34.967420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ff1e091b-2dd3-4dda-aa89-890544a4b4cc · outbound

This paper cites Distance measures for speech process- ing,.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Distance measures for speech process- ing,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:34.283710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c797946e-3184-4032-94bd-8df5cd3da96d · outbound

This paper cites SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics.

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:34.351568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f77411c-4ea9-4705-9018-8d7cba7d55e2 · outbound

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

FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge Evaluation metrics for generative speech en- hancement methods: Issues and perspectives,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:01:34.783696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation bb16165a-f05c-4d15-a8f1-15c85410c3ea · inbound