Paper Citation Record · LEDGER

Adversarially Trained End-to-end Korean Singing Voice Synthesis System

As of 20 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:1908.01919.

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

pith.paper-citation-record.v1
1908.01919 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T15:04:32.900274Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T15:04:32.627267Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-14T15:04:33.320936Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy19
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 934fab5a-717e-438b-b020-d4f6cfbebe3d · outbound

This paper cites For example, three SVS sys- tems based on DNN, LSTM, and Wavenet architecture were proposed, respectively [4, 5, 6].

Adversarially Trained End-to-end Korean Singing Voice Synthesis System For example, three SVS sys- tems based on DNN, LSTM, and Wavenet architecture were proposed, respectively [4, 5, 6]

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.967134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3fb0fad9-ed63-4060-9cb4-6805beee4ee6 · outbound

This paper cites Recently, the end-to-end TTS system, which is trained as an autoregressive manner, such as Tacotron[8], Deep voice[9], is showing better performance than the conventional method.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Recently, the end-to-end TTS system, which is trained as an autoregressive manner, such as Tacotron[8], Deep voice[9], is showing better performance than the conventional method

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.941450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 92949faf-371f-4e48-bda3-c872d050e3eb · outbound

This paper cites Adversarially Trained End-to-end Korean Singing Voice Synthesis System.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Adversarially Trained End-to-end Korean Singing Voice Synthesis System

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-08-14T15:04:33.336154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 741b659e-30c1-4e2f-868a-8b3053bf6ae3 · outbound

This paper cites Dataset Since there is no publicly available Korean singing voice dataset, we created the dataset as follows.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Dataset Since there is no publicly available Korean singing voice dataset, we created the dataset as follows

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.884267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7aeed66b-7dba-4fe9-bc1c-61062e500dc4 · outbound

This paper cites We showed that using text information to model the phonetic enhancement mask actually worked, and produced more accurate pronunciation.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System We showed that using text information to model the phonetic enhancement mask actually worked, and produced more accurate pronunciation

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.831986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7531fb99-55f1-4da9-9a43-104570be3dd2 · outbound

This paper cites In the case of sound quality, methods 1 and 2 did not sig- niﬁcantly affect the improvement, but the applying method 3 Figure 3: Generated spectrograms.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System In the case of sound quality, methods 1 and 2 did not sig- niﬁcantly affect the improvement, but the applying method 3 Figure 3: Generated spectrograms

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.861589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a1c2393c-8eda-45d1-a8fb-e5f515805a8f · outbound

This paper cites First, in order to enter pitch information, we added pitch encoders with the same structure as text encoders.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System First, in order to enter pitch information, we added pitch encoders with the same structure as text encoders

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.910285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f23577e3-7b8d-47f7-9906-f76174edb6b3 · outbound

This paper cites an unresolved cited work.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-14T15:04:33.809414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a24a3a0f-946f-4805-8aae-db02de1e9633 · outbound

This paper cites Concatenation-based midi-to-singing voice syn- thesis,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Concatenation-based midi-to-singing voice syn- thesis,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.785392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dcc44047-ebb8-4631-b94d-415def622cb0 · outbound

This paper cites Sample- based singing voice synthesizer using spectral models and source- ﬁlter decomposition,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Sample- based singing voice synthesizer using spectral models and source- ﬁlter decomposition,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.748347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3c900d7c-25d3-4f04-b803-982c108a5b2a · outbound

This paper cites V ocaloid-commercial singing syn- thesizer based on sample concatenation,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System V ocaloid-commercial singing syn- thesizer based on sample concatenation,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.717634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 69fa44f2-3c68-4a85-afbc-9284035ec4c4 · outbound

This paper cites Singing voice synthesis based on deep neural net- works.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Singing voice synthesis based on deep neural net- works

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.685795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5cb98ab3-756f-4131-9ce7-4f0ee8ea61ae · outbound

This paper cites Korean singing voice synthesis system based on an lstm recurrent neural network,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Korean singing voice synthesis system based on an lstm recurrent neural network,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.656525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 54a0a82a-e11c-41a9-967b-08686ecc9f4e · outbound

This paper cites A neural parametric singing synthe- sizer modeling timbre and expression from natural songs,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System A neural parametric singing synthe- sizer modeling timbre and expression from natural songs,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.634598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8acdb953-2939-4c27-ba9b-86d6717b1f96 · outbound

This paper cites Efﬁciently train- able text-to-speech system based on deep convolutional networks with guided attention,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Efﬁciently train- able text-to-speech system based on deep convolutional networks with guided attention,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.604675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1faef748-c156-4efb-89a4-05875a5c9a7e · outbound

This paper cites Tacotron: Towards End-to-End Speech Synthesis.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Tacotron: Towards End-to-End Speech Synthesis

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.758890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a2e93d7-0729-4df0-ae17-de1b5bb3d99c · outbound

This paper cites Deep voice 2: Multi-speaker neural text- to-speech,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Deep voice 2: Multi-speaker neural text- to-speech,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.577183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 67ee3b95-5455-4daa-933c-9b9c381ee10e · outbound

This paper cites Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.775499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b152ab93-0151-4dc2-a6bd-3f3f2728a6cb · outbound

This paper cites Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.790427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 234074e7-8471-4005-86aa-21266d27950c · outbound

This paper cites Semi-Supervised Training for Improving Data Efficiency in End-to-End Speech Synthesis.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Semi-Supervised Training for Improving Data Efficiency in End-to-End Speech Synthesis

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.798183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a427ff8-e219-4f41-8973-21b2d699c21e · outbound

This paper cites Speech band- width extension using generative adversarial networks,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Speech band- width extension using generative adversarial networks,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.807982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41e18110-478a-4b03-a7a7-974243325b8a · outbound

This paper cites cGANs with Projection Discriminator.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System cGANs with Projection Discriminator

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.815332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bcf71f6-6ed7-4dd2-8aea-986e76cf7b17 · outbound

This paper cites Large Scale GAN Training for High Fidelity Natural Image Synthesis.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Large Scale GAN Training for High Fidelity Natural Image Synthesis

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.822440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2a14b5d-d811-4154-ae17-c8a4e63fc977 · outbound

This paper cites Signal estimation from modiﬁed short- time fourier transform,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Signal estimation from modiﬁed short- time fourier transform,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.530052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation be5dc81e-362c-44c9-946a-0119c5b36307 · outbound

This paper cites WaveNet: A Generative Model for Raw Audio.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System WaveNet: A Generative Model for Raw Audio

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.834775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef683e37-81fe-411d-9374-eb236f08c699 · outbound

This paper cites Dropout: a simple way to prevent neural net- works from overﬁtting,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Dropout: a simple way to prevent neural net- works from overﬁtting,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.501667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c8b0ea22-3e8a-450b-ad4b-b4a82ea1975f · outbound

This paper cites Improved training of wasserstein gans,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Improved training of wasserstein gans,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.470197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b7d3dad6-f809-4d86-8709-8728d30bd4d5 · outbound

This paper cites Spectral Normalization for Generative Adversarial Networks.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Spectral Normalization for Generative Adversarial Networks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.854952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b670dd15-f368-41f3-afe7-c523ff48dde9 · outbound

This paper cites Which Training Methods for GANs do actually Converge?.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Which Training Methods for GANs do actually Converge?

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.867284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4eb64ee-8e14-48fe-b9c1-9f8bb0350c66 · outbound

This paper cites Generative adver- sarial nets,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Generative adver- sarial nets,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.439146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 86253747-3d7a-4b5a-9239-49c409716da6 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Adam: A Method for Stochastic Optimization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.883317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4972dbcd-278c-4656-a3bc-3f6b8164bb5a · outbound

This paper cites Understanding the difﬁculty of train- ing deep feedforward neural networks,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System Understanding the difﬁculty of train- ing deep feedforward neural networks,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-14T15:04:32.890770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72259870-852f-4d7e-b8dc-92deaf44c5f9 · outbound

This paper cites World: a vocoder-based high-quality speech synthesis system for real-time applications,.

Adversarially Trained End-to-end Korean Singing Voice Synthesis System World: a vocoder-based high-quality speech synthesis system for real-time applications,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:04:33.372021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 92949faf-371f-4e48-bda3-c872d050e3eb · inbound