Paper Citation Record · LEDGER

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms

As of 9 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2506.13709.

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

pith.paper-citation-record.v1
2506.13709 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:30:35.426830Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:30:35.281047Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T00:30:35.591170Z

Reference resolution

42 of 42 outbound references displayed

verified exact2
verified fuzzy29
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3120960a-32d8-473d-99a3-37f5ceba9f40 · outbound

This paper cites an unresolved cited work.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:30:35.968338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 25873659-1329-428d-ba3e-1c9cb7b1f49d · outbound

This paper cites SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:30:35.594901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f3c1f7e4-37ef-45a1-99b7-92266d5c6309 · outbound

This paper cites Front-end processing systems We aim to test our system on speech processed by different front-end algorithms to evaluate its generalization performance.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Front-end processing systems We aim to test our system on speech processed by different front-end algorithms to evaluate its generalization performance

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.947504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6415ca1a-2130-4255-a709-6ed702329607 · outbound

This paper cites Comparison with front-end-specific baselines We first evaluate SpeechRefiner against state-of-the-art refin- ers designed for specific front-end tasks.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Comparison with front-end-specific baselines We first evaluate SpeechRefiner against state-of-the-art refin- ers designed for specific front-end tasks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.925582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 76a13b62-46e4-4868-a768-9ee6ecf713c1 · outbound

This paper cites Trained on data derived from a single impairment source, SpeechRefiner demonstrated re- markable generalization capabilities across a variety of unseen front-end algorithms.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Trained on data derived from a single impairment source, SpeechRefiner demonstrated re- markable generalization capabilities across a variety of unseen front-end algorithms

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.914745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 07c7a5b9-f1b0-4bf6-8827-867d43166402 · outbound

This paper cites 62401377, Shenzhen Science and Technology Program (Shenzhen Key Laboratory, Grant No.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms 62401377, Shenzhen Science and Technology Program (Shenzhen Key Laboratory, Grant No

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.904386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 081be2da-21d3-4d40-a5c3-ec5d6d13bb86 · outbound

This paper cites Tasnet: time-domain audio separa- tion network for real-time, single-channel speech separation,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Tasnet: time-domain audio separa- tion network for real-time, single-channel speech separation,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.838325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2ee4dad0-f678-469b-be58-26c4266a8182 · outbound

This paper cites RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:30:35.580078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f38d5ecc-5d9a-4993-bc6c-27f18e203167 · outbound

This paper cites A review of multi-objective deep learning speech denoising methods,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms A review of multi-objective deep learning speech denoising methods,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.893750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7100e415-0564-474e-a62b-616157fa8d05 · outbound

This paper cites an unresolved cited work.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:30:35.883567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bd7e8a93-ba9f-47c8-9ad4-49d2ad54bceb · outbound

This paper cites Supervised speech separation based on deep learning: An overview,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Supervised speech separation based on deep learning: An overview,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.872130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 427fd728-a477-4958-bb9a-7d3a2d23d3bf · outbound

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

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Conv-tasnet: Surpassing ideal time– frequency magnitude masking for speech separation,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:30:35.319547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5066caf9-40b3-443d-8993-2fc370f03074 · outbound

This paper cites Neural target speech extraction: An overview,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Neural target speech extraction: An overview,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:30:35.323688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c547f5-d61f-47cb-810f-2539d207123a · outbound

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

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Sdr– half-baked or well done?

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.849068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 113ceae6-6f4d-47ca-b0f3-92e6d5cb5700 · outbound

This paper cites Miipher: A ro- bust speech restoration model integrating self-supervised speech and text representations,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Miipher: A ro- bust speech restoration model integrating self-supervised speech and text representations,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.766162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 28195c6e-c597-49b0-827a-6a3dff56e6ec · outbound

This paper cites an unresolved cited work.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:30:35.935545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dc0bb4f1-196b-4332-85c9-ed64ddb6306e · outbound

This paper cites Rad-net 2: A causal two-stage repairing and denois- ing speech enhancement network with knowledge distillation and complex axial self-attention,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Rad-net 2: A causal two-stage repairing and denois- ing speech enhancement network with knowledge distillation and complex axial self-attention,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.827454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b0a846e2-ae79-43f4-907c-93998380c44d · outbound

This paper cites Autoprep: An automatic preprocessing framework for in-the-wild speech data,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Autoprep: An automatic preprocessing framework for in-the-wild speech data,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.816983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d5bfa731-0b0b-4551-a87c-ef16969fa8e3 · outbound

This paper cites Wenetspeech4tts: A 12,800-hour mandarin tts corpus for large speech generation model bench- mark,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Wenetspeech4tts: A 12,800-hour mandarin tts corpus for large speech generation model bench- mark,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.806822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e943fbdb-ae53-4ca4-8124-64383fa87f3e · outbound

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

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Dnsmos: A non-intrusive perceptual objective speech quality metric to evaluate noise sup- pressors,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.796789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d725084a-67dd-471b-8d38-892849f9010a · outbound

This paper cites The loss function for CFM is expressed as: LCF M(θ) =Et,q(x1),pt(x|x1)∥vt(x; θ) − ut(x|x1)∥2.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms The loss function for CFM is expressed as: LCF M(θ) =Et,q(x1),pt(x|x1)∥vt(x; θ) − ut(x|x1)∥2

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.957835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 800260f2-3466-48b1-9ba7-f4def1cb0620 · outbound

This paper cites Icassp 2024 speech signal improvement challenge,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Icassp 2024 speech signal improvement challenge,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.786578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0a5aa18f-4749-49fb-b9ae-6f30523ca017 · outbound

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

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms V oicefixer: A unified framework for high-fidelity speech restoration,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.775888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f39bf6c4-9d03-4ad1-a38f-72dba3cb89cf · outbound

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

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Storm: A diffusion-based stochastic regeneration model for speech en- hancement and dereverberation,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.755883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d4edd344-60fe-4b47-b743-999271f0b6a7 · outbound

This paper cites Diffiner: A versatile diffusion-based generative refiner for speech enhancement,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Diffiner: A versatile diffusion-based generative refiner for speech enhancement,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.745254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5c4a6b26-d17d-449a-8e9a-a4a1807bf45f · outbound

This paper cites Diffusion-based signal refiner for speech separation,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Diffusion-based signal refiner for speech separation,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:30:35.375508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b746e96-9e27-47c8-a69f-525b0cd203de · outbound

This paper cites Separate and diffuse: Us- ing a pretrained diffusion model for better source separation,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Separate and diffuse: Us- ing a pretrained diffusion model for better source separation,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.735341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 22270425-893b-4e09-b595-059f8b62e0f0 · outbound

This paper cites Noise-robust speech separation with fast generative correction,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Noise-robust speech separation with fast generative correction,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.722357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fa2f77af-d0e8-4450-af09-406ee421086b · outbound

This paper cites Flow matching for generative modeling,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Flow matching for generative modeling,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.709089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9b942e08-405c-4724-8954-c0ca87c3e087 · outbound

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

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Conformer: Convolution- augmented transformer for speech recognition,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.697056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e9fb4313-6eb4-4c8e-a388-15a34005b87b · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Roformer: Enhanced transformer with rotary position embedding,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.684682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1a3f87aa-b495-45fa-86c1-6831b5da1c8a · outbound

This paper cites Train short, test long: At- tention with linear biases enables input length extrapolation,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Train short, test long: At- tention with linear biases enables input length extrapolation,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.672832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 513f7c56-5181-4066-ab7d-01fffc8e987d · outbound

This paper cites Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:30:35.396683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f2fc4d-5211-4c85-a933-16213b3d393f · outbound

This paper cites Conditional diffusion probabilistic model for speech en- hancement,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Conditional diffusion probabilistic model for speech en- hancement,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.662060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1ed69ef0-491a-41c1-be2f-a1a6b1f1a322 · outbound

This paper cites Investigating rnn-based speech enhancement methods for noise- robust text-to-speech.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Investigating rnn-based speech enhancement methods for noise- robust text-to-speech

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:30:35.403803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de3a22f9-3b71-4b70-a7e4-5e37da78bb46 · outbound

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

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Speech enhancement and dereverberation with diffusion-based generative models,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.643733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 64c6161a-cf9d-4d0b-bc16-aa0da80e4d35 · outbound

This paper cites Attention is all you need in speech separation,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Attention is all you need in speech separation,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.633290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e503fbd7-3814-4625-8716-bed84fe69c16 · outbound

This paper cites LibriMix: An Open-Source Dataset for Generalizable Speech Separation.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms LibriMix: An Open-Source Dataset for Generalizable Speech Separation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:30:35.412898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac869582-0f68-4170-9792-971b4a90ed2a · outbound

This paper cites Spex+: A complete time domain speaker extraction network,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Spex+: A complete time domain speaker extraction network,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.623164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c92fd0b3-2d4b-4622-beaf-06f6b1347b7b · outbound

This paper cites Muse: Multi-modal target speaker extraction with visual cues,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Muse: Multi-modal target speaker extraction with visual cues,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:30:35.612754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 34b1ff22-ef2d-433a-89ec-88726927f0d8 · outbound

This paper cites LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T00:30:35.423748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7c708e0-ec04-4340-8da6-ec9c8050da49 · outbound

This paper cites Grad-tts: A diffusion probabilistic model for text-to-speech,.

SpeechRefiner: Towards Perceptual Quality Refinement for Front-End Algorithms Grad-tts: A diffusion probabilistic model for text-to-speech,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:30:35.426830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 25873659-1329-428d-ba3e-1c9cb7b1f49d · inbound