Paper Citation Record · LEDGER

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration

As of 23 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 2 inbound Pith citation observations for arXiv:2505.04457.

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

pith.paper-citation-record.v1
2505.04457 v4

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:32:42.771927Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:16:41.772452Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T17:16:21.330378Z

Reference resolution

55 of 55 outbound references displayed

verified exact1
verified fuzzy29
unresolved24
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1892013c-9568-464b-80ce-723bf99c7ec3 · outbound

This paper cites Parametric resynthesis with neural vocoders,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Parametric resynthesis with neural vocoders,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.577489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 778a495f-e658-4be3-ae75-6a7c9bd758ec · outbound

This paper cites SelfRemaster: Self-supervised speech restoration with analysis-by-synthesis approach using channel modeling,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration SelfRemaster: Self-supervised speech restoration with analysis-by-synthesis approach using channel modeling,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.581647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cd3b168-3ff4-41d9-ae23-d2334f44a0e3 · outbound

This paper cites HiFi-GAN-2: Studio-quality speech enhancement via generative adversarial networks conditioned on acoustic features,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration HiFi-GAN-2: Studio-quality speech enhancement via generative adversarial networks conditioned on acoustic features,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.585194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95ada63f-d7a9-4d8d-bf3c-c71042b6e100 · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration V oiceFixer: A unified framework for high-fidelity speech restoration,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.588750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0df2acf-bee1-4b3e-9940-dd1ea559941e · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Universal Speech Enhancement with Score-based Diffusion

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.592156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be161f6f-05f5-4344-8764-1b6fecee3df7 · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Miipher: A robust speech restoration model integrating self-supervised speech and text representations,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.524115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d2483b2c-fa1a-4264-8060-f215cd0916f1 · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Speech enhancement and dereverberation with diffusion-based generative models,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.513705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 73686880-e64b-49e2-967e-5ce7a52a83d4 · outbound

This paper cites Diffusion models for audio restoration: A review,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Diffusion models for audio restoration: A review,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.603671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 615a9790-bf7b-4de2-a0c3-989fca2d99c1 · outbound

This paper cites Universal score-based speech enhancement with high content preservation,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Universal score-based speech enhancement with high content preservation,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.607148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 585c329c-d32d-47ab-8fbc-992d7eee9ba9 · outbound

This paper cites LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.611362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf7b59b4-66aa-4be7-8a72-56662bc83d58 · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Genhancer: High-fidelity speech enhancement via generative modeling on discrete codec tokens,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.615300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d27fdb2b-17db-4015-9151-d9a958bf881f · outbound

This paper cites Joint semantic knowledge distillation and masked acoustic modeling for full-band speech restoration with improved intelligibility,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Joint semantic knowledge distillation and masked acoustic modeling for full-band speech restoration with improved intelligibility,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.619218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d94742fa-34c0-49de-bee9-c52637cf941a · outbound

This paper cites DiTSE: High-fidelity generative speech enhancement via latent diffusion transformers,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration DiTSE: High-fidelity generative speech enhancement via latent diffusion transformers,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.622796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16073fb8-1f62-48f9-a256-5dc406c3b5c6 · outbound

This paper cites LibriTTS-R: A restored multi-speaker text- to-speech corpus,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration LibriTTS-R: A restored multi-speaker text- to-speech corpus,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.478525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c3a24491-1321-4643-831e-51358c5c4a15 · outbound

This paper cites FLEURS-R: A restored multilingual speech corpus for generation tasks,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration FLEURS-R: A restored multilingual speech corpus for generation tasks,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.467600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 84d3122f-ee83-494f-9072-6db649542fc2 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.632918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2d1c267-72e2-4e99-8d3f-866c30c6d5c4 · outbound

This paper cites GPT-4 Technical Report.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration GPT-4 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.636339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d461d7bc-73da-4704-8a08-68406539fc23 · outbound

This paper cites Moshi: a speech-text foundation model for real-time dialogue.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Moshi: a speech-text foundation model for real-time dialogue

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.639502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51fdadb0-5a67-494b-a17f-22dff5ed06e7 · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.643117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8467dce-e907-4d8e-a05d-27a56c737e5c · outbound

This paper cites Towards a unified view of parameter- efficient transfer learning,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Towards a unified view of parameter- efficient transfer learning,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.456216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c61cbd93-9bee-461a-b9ec-f25c3c9507a1 · outbound

This paper cites WaveFit: An iterative and non- autoregressive neural vocoder based on fixed-point iteration,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration WaveFit: An iterative and non- autoregressive neural vocoder based on fixed-point iteration,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.650195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9bda9ef-65bb-4b20-a0b9-5fb924c65bf5 · outbound

This paper cites Ten lessons from three generations shaped google’s tpuv4i : Industrial product,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Ten lessons from three generations shaped google’s tpuv4i : Industrial product,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.440054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2770856e-7a88-4d33-aa92-bcd5f315043d · outbound

This paper cites Self-supervised learning with random- projection quantizer for speech recognition,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Self-supervised learning with random- projection quantizer for speech recognition,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.429272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 53636106-62be-4ec5-8c96-a6039a9aec64 · outbound

This paper cites wav2vec 2.0: A framework for self- supervised learning of speech representations,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration wav2vec 2.0: A framework for self- supervised learning of speech representations,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.418184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d079c908-6a74-4505-9183-dff2337e4a70 · outbound

This paper cites w2v-BERT: Combining contrastive learning and masked language modeling for self-supervised speech pre- training,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration w2v-BERT: Combining contrastive learning and masked language modeling for self-supervised speech pre- training,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.407977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 67e8fe65-f6a3-4b73-a393-0e3259c58ce5 · outbound

This paper cites Hubert: Self-supervised speech representation learning by masked prediction of hidden units,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Hubert: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.667269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0048fb43-db67-41a6-a2c8-f54870cc487d · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Wavlm: Large-scale self-supervised pre-training for full stack speech processing,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.670280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbe5840e-0e8a-4c5d-8779-49d389b9969a · outbound

This paper cites V oice conversion with just nearest neighbors,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration V oice conversion with just nearest neighbors,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.673735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dd4b508-8b0d-45cb-addf-509425016c4e · outbound

This paper cites Vec-Tok Speech: speech vectorization and tokenization for neural speech generation.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Vec-Tok Speech: speech vectorization and tokenization for neural speech generation

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.677294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2f635e1-73ec-46ff-9d4a-2650381d9c76 · outbound

This paper cites DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.392944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2d1e8a46-6c55-4459-8e94-c30730d8cce9 · outbound

This paper cites Fast spectrogram inversion using multi-head convolutional neural networks,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Fast spectrogram inversion using multi-head convolutional neural networks,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.382625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 871215ce-ed79-44db-9e98-2a8a6e24db45 · outbound

This paper cites FiLM: Visual reasoning with a general conditioning layer,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration FiLM: Visual reasoning with a general conditioning layer,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.373206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2ebaffcf-0a71-4e91-b653-52c6c3ecbe5b · outbound

This paper cites WaveGrad: Estimating gradients for waveform generation,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration WaveGrad: Estimating gradients for waveform generation,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.363030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 65ba69fd-8587-4349-bc89-a3655b1cb8cf · outbound

This paper cites URGENT challenge 2025 baseline,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration URGENT challenge 2025 baseline,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.353482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3b08f8d3-3f65-490c-b8c3-6ba4d88883a7 · outbound

This paper cites PromptTTS++: Controlling speaker identity in prompt-based text-to-speech using natural language descrip- tions,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration PromptTTS++: Controlling speaker identity in prompt-based text-to-speech using natural language descrip- tions,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.344013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 15c7dead-5fb3-4453-8ee5-ed72b6391fe2 · outbound

This paper cites Xtts: a massively multilingual zero-shot text-to-speech model,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Xtts: a massively multilingual zero-shot text-to-speech model,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.332596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c291ea86-2bb2-4ca4-ab4f-a5d2346c982b · outbound

This paper cites Natural language guidance of high-fidelity text-to-speech with synthetic annotations.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Natural language guidance of high-fidelity text-to-speech with synthetic annotations

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.703745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dd4c81b-8604-4235-a1a6-3cbc42f9ae57 · outbound

This paper cites CoVoST: A diverse multilingual speech-to-text translation corpus,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration CoVoST: A diverse multilingual speech-to-text translation corpus,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.322714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ee5e7ca5-5d77-4210-9447-935d32ec8e32 · outbound

This paper cites CVSS corpus and massively multilingual speech-to-speech translation,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration CVSS corpus and massively multilingual speech-to-speech translation,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.313287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bf39bc81-3527-4e8f-839f-5ad6dc60da75 · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Mls: A large-scale multilingual dataset for speech research,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.302906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e4c9d48a-cef2-4e97-b66e-d99e56c7e9a6 · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Fleurs: Few-shot learning evaluation of universal representations of speech,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.293112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fd8c7d3d-9924-4d7e-9f71-fafb58022c4e · outbound

This paper cites Image method for efficiently simulating small-room acoustics,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Image method for efficiently simulating small-room acoustics,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.720338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ae9d80c-0921-4630-96ce-4f332333bc93 · outbound

This paper cites HiFi-GAN: High-fidelity denoising and dereverberation based on speech deep features in adversarial networks,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration HiFi-GAN: High-fidelity denoising and dereverberation based on speech deep features in adversarial networks,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.277235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5679b8be-58e7-4077-ac28-39ead45a4358 · outbound

This paper cites Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,

Reference 44

Resolution: malformed identifier; no resolver link, observed 2026-08-15T23:32:42.727294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca40632e-e652-42b8-9eac-909d4dcdc76e · outbound

This paper cites Transfer learning from speaker verification to multispeaker text-to-speech synthesis,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Transfer learning from speaker verification to multispeaker text-to-speech synthesis,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.730687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04b3664d-ceb5-48fb-80d4-41e322ac1adb · outbound

This paper cites Sample efficient adaptive text-to-speech,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Sample efficient adaptive text-to-speech,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:42.738754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c57575c-e60e-4e88-bd6f-cfd191fedb24 · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.255856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation aa719d13-24d4-4cd8-9a89-27f858593ef9 · outbound

This paper cites SQuId: Measuring Speech Naturalness in Many Languages.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration SQuId: Measuring Speech Naturalness in Many Languages

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:32:42.810919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c001b40f-7490-4293-bead-05baeefdbca3 · outbound

This paper cites Tf-gridnet: Making time-frequency domain models great again for monaural speaker separation,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Tf-gridnet: Making time-frequency domain models great again for monaural speaker separation,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.245389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation de58b87a-7c84-4eda-8fa4-cd8f287a196b · outbound

This paper cites The design for the Wall Street Journal-based CSR corpus,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration The design for the Wall Street Journal-based CSR corpus,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.234101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4cd4ef79-a611-490d-98b4-b348c5c6a614 · outbound

This paper cites Common V oice: A massively-multilingual speech corpus,.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Common V oice: A massively-multilingual speech corpus,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.222412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 536c3c56-7a8b-458a-a2aa-494a2af2134f · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration mHuBERT-147: A Compact Multilingual HuBERT Model,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.212033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ad065ed2-98ad-4d8a-9582-eb659a01789f · outbound

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

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Towards robust speech representation learning for thousands of languages,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.201845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0d47ae0f-f161-404f-80d1-33fd0b826017 · outbound

This paper cites Nakata, https://github.com/Wataru-Nakata/miipher.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Nakata, https://github.com/Wataru-Nakata/miipher

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.192008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7a4c618e-962f-4008-b88c-bcbd163b7e1f · outbound

This paper cites Ikemiya, https://github.com/yukara-ikemiya/wavefit-pytorch.

Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration Ikemiya, https://github.com/yukara-ikemiya/wavefit-pytorch

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:32:43.181306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 2f81d4fb-c484-47a4-a834-a2affe547eb0 · inbound

ReverbMiipher: Generative Speech Restoration meets Reverberation Characteristics Controllability cites this paper.

ReverbMiipher: Generative Speech Restoration meets Reverberation Characteristics Controllability Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T23:16:41.772452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08e637f5-1af5-4aa6-9c46-10db19b147a8 · inbound

Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement cites this paper.

Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:16:21.332886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.