Paper Citation Record · LEDGER

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation

As of 7 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2607.11630.

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

pith.paper-citation-record.v1
2607.11630 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-14T04:15:55.752679Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T04:15:55.752679Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy0
unresolved44
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0afe5fdd-1714-4a9f-96a4-809daecddcbc · outbound

This paper cites Interactive Audiovisual Digital Twins of Performance Venues.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Interactive Audiovisual Digital Twins of Performance Venues

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a741e0e3-71d4-4356-8a6a-8ed0288d2b0a · outbound

This paper cites Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82298051-0556-4be9-9cc8-c6234c878a44 · outbound

This paper cites Full fine-tuning With full fine-tuning all parameters of the pretrained SE model are updated during SVS training.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Full fine-tuning With full fine-tuning all parameters of the pretrained SE model are updated during SVS training

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9beebe45-b5a8-4da2-9d9a-ea8188f0c59e · outbound

This paper cites Pretraining and adaptation All models in this work operate at a sampling rate of48 kHzand are initialized from pretrained checkpoints.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Pretraining and adaptation All models in this work operate at a sampling rate of48 kHzand are initialized from pretrained checkpoints

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 104ef5cf-f3c8-458a-8cce-bf3fe5be53fe · outbound

This paper cites The SGM, which utilizes a noise-conditional score network (NCSN++) [22] as its backbone, was pretrained for SE on the EARS-WHAM dataset [23] (approx.87 h).

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation The SGM, which utilizes a noise-conditional score network (NCSN++) [22] as its backbone, was pretrained for SE on the EARS-WHAM dataset [23] (approx.87 h)

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1942b4a6-2258-4d32-b214-d2717e6b1963 · outbound

This paper cites from scratch.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation from scratch

Reference 6

Resolution: malformed identifier; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecec330c-f292-4116-8417-c74c1ef3dcac · outbound

This paper cites While full fine-tuning achieves the best SVS performance, our results show that LoRA enables domain adaptation while preserving the original model capabilities.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation While full fine-tuning achieves the best SVS performance, our results show that LoRA enables domain adaptation while preserving the original model capabilities

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c5e8c2e-6bba-49ea-8f5d-15befad2f5d9 · outbound

This paper cites INTERSPEECH 2021 deep noise suppression challenge,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation INTERSPEECH 2021 deep noise suppression challenge,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da0f9293-1f63-4442-aed1-af5aa45a6746 · outbound

This paper cites ICASSP 2022 deep noise suppression challenge,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation ICASSP 2022 deep noise suppression challenge,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4474c44a-4327-4cd3-997d-a0a02280ef59 · outbound

This paper cites ICASSP 2023 deep noise suppression challenge,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation ICASSP 2023 deep noise suppression challenge,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fceb123f-e7bc-4d9f-93d7-c5668c71c019 · outbound

This paper cites URGENT challenge: Universality, robustness, and generalizability for speech en- hancement,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation URGENT challenge: Universality, robustness, and generalizability for speech en- hancement,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1d4e112-15d8-4046-a1df-3c1d429a2f80 · outbound

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

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Speech enhancement and dereverberation with diffusion-based gen- erative models,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9138df4-2fdc-4057-b71e-9295cf4294f8 · outbound

This paper cites StoRM: A diffusion-based stochastic regeneration model for speech enhance- ment and dereverberation,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation StoRM: A diffusion-based stochastic regeneration model for speech enhance- ment and dereverberation,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88d486f0-c140-447f-bf1e-29577ee82c4e · outbound

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

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Universal score- based speech enhancement with high content preservation,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4c21d0e-358c-4aec-8269-d60d1afd6bfb · outbound

This paper cites Diffusion-based signal refiner for speech enhancement and separa- tion,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Diffusion-based signal refiner for speech enhancement and separa- tion,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a87fc1f7-b28b-4d0d-b4c4-3c5b5e758271 · outbound

This paper cites The MUSDB18 corpus for music separation,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation The MUSDB18 corpus for music separation,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 548d57f5-8fe9-4b38-8004-1e818303ffa4 · outbound

This paper cites MoisesDB: A dataset for source separation beyond 4-stems,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation MoisesDB: A dataset for source separation beyond 4-stems,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf0cdf9a-fdae-4920-832b-abc098e6d83a · outbound

This paper cites High fidelity speech enhancement with band-split RNN,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation High fidelity speech enhancement with band-split RNN,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97d50998-865e-4df1-ae34-7b320b314446 · outbound

This paper cites Music source separation with band-split RNN,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Music source separation with band-split RNN,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff03bd4b-ae43-494e-936f-ef8369f5e8be · outbound

This paper cites Towards reliable objective evaluation metrics for generative singing voice sepa- ration models,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Towards reliable objective evaluation metrics for generative singing voice sepa- ration models,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58601b24-6f13-455b-a5b4-057e57401fa6 · outbound

This paper cites Diff-VS: Efficient audio-aware diffusion u-net for vocals separation,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Diff-VS: Efficient audio-aware diffusion u-net for vocals separation,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edd4ceb4-9a5f-4677-a528-40c97128c7f5 · outbound

This paper cites Music source restora- tion,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Music source restora- tion,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ad52ee8-51ac-46af-b26c-1731d0918f26 · outbound

This paper cites Overcoming catastrophic forgetting in neural networks,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Overcoming catastrophic forgetting in neural networks,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23a09c2e-f0ea-4667-a604-86100de87990 · outbound

This paper cites SERIL: Noise adaptive speech enhancement using regularization-based incre- mental learning,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation SERIL: Noise adaptive speech enhancement using regularization-based incre- mental learning,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43b71d03-d34b-432f-87ab-d57eb2d330dc · outbound

This paper cites LoRA: Low-rank adaptation of large language models,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation LoRA: Low-rank adaptation of large language models,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56b44a23-97ec-4b6e-9e0a-29ffcc1ab5b9 · outbound

This paper cites Parameter- efficient transfer learning of audio spectrogram transformers,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Parameter- efficient transfer learning of audio spectrogram transformers,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45a48e11-c050-4a55-96f1-5681d73f10ef · outbound

This paper cites Improving anomalous sound detection via low-rank adaptation fine- tuning of pre-trained audio models,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Improving anomalous sound detection via low-rank adaptation fine- tuning of pre-trained audio models,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3d3ecfc-cade-482f-a8b1-6f73da1ecd2f · outbound

This paper cites Mel-band-roformer-vocal-model,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Mel-band-roformer-vocal-model,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e8cb96f-ce30-4d58-a659-f7db688a16de · outbound

This paper cites Score-based generative modeling through stochastic differential equations,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Score-based generative modeling through stochastic differential equations,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ddf2be8-32f4-4714-8b88-68c1c5320f2c · outbound

This paper cites EARS: An anechoic fullband speech dataset benchmarked for speech enhancement and dereverberation,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation EARS: An anechoic fullband speech dataset benchmarked for speech enhancement and dereverberation,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a714549f-4d88-4be3-8464-d672434e240a · outbound

This paper cites MSRBench: A benchmarking dataset for music source restoration,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation MSRBench: A benchmarking dataset for music source restoration,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1861a3bb-29df-4a8a-b9f0-e3569fcaab11 · outbound

This paper cites EBU R 128: Loudness normalisation and permitted maximum level of audio signals,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation EBU R 128: Loudness normalisation and permitted maximum level of audio signals,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25baf78e-ef1a-412d-91c3-e786aa233765 · outbound

This paper cites Generative modeling by estimating gradients of the data distribution,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Generative modeling by estimating gradients of the data distribution,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5929d63f-5b52-4de8-8487-2f741987b688 · outbound

This paper cites PEFT: State-of-the-art parameter-efficient fine- tuning methods,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation PEFT: State-of-the-art parameter-efficient fine- tuning methods,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ef97e39-e7b1-43b5-bd39-1cae8cfee359 · outbound

This paper cites Delving deep into rectifiers: Sur- passing human-level performance on imagenet classification,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Delving deep into rectifiers: Sur- passing human-level performance on imagenet classification,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7c35e37-7596-4aa7-bcba-a248c1f3f6d0 · outbound

This paper cites Performance measurement in blind audio source separation,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Performance measurement in blind audio source separation,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52c31c02-a711-4654-936f-6fed72920180 · outbound

This paper cites TorchMetrics - measuring reproducibility in PyTorch,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation TorchMetrics - measuring reproducibility in PyTorch,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 066213b2-69f4-4506-a21c-5dccd42b0bfc · outbound

This paper cites MERT: Acous- tic music understanding model with large-scale self-supervised train- ing,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation MERT: Acous- tic music understanding model with large-scale self-supervised train- ing,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8f71c21-3886-42a8-be90-d73134c7e33f · outbound

This paper cites auraloss: Audio focused loss functions in PyTorch,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation auraloss: Audio focused loss functions in PyTorch,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21056434-f1a2-4b4c-ab62-0f090cbbf0a8 · outbound

This paper cites Embedding-based intrusive evaluation metrics for musical source separation using MERT representations,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Embedding-based intrusive evaluation metrics for musical source separation using MERT representations,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50953a67-6f17-486c-b51b-075baa9ceddd · outbound

This paper cites SDR – Half- baked or well done?.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation SDR – Half- baked or well done?

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74dd1257-64b8-4722-a0f2-288ba9dcec46 · outbound

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

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d48a0466-8710-46ed-b4b2-622f6bf62a2c · outbound

This paper cites Distillation and pruning for scalable self- supervised representation-based speech quality assessment,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Distillation and pruning for scalable self- supervised representation-based speech quality assessment,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e9475b8-0c10-456f-971e-ca7acfb6f5e3 · outbound

This paper cites Mel-RoFormer for vocal separa- tion and vocal melody transcription,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation Mel-RoFormer for vocal separa- tion and vocal melody transcription,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 659ba9bf-fb80-4388-9367-80345d891cb7 · outbound

This paper cites ptflops: A flops counting tool for neural networks in pytorch framework,.

Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation ptflops: A flops counting tool for neural networks in pytorch framework,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-14T04:15:55.752679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a741e0e3-71d4-4356-8a6a-8ed0288d2b0a · inbound