{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:19:27Z","timestamp":1753600767000,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094854","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Optimal Transport in Diffusion Modeling for Conversion Tasks in Audio Domain"],"prefix":"10.1109","author":[{"given":"Vadim","family":"Popov","sequence":"first","affiliation":[{"name":"Huawei Noah’s Ark Lab"}]},{"given":"Amantur","family":"Amatov","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab"}]},{"given":"Mikhail","family":"Kudinov","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab"}]},{"given":"Vladimir","family":"Gogoryan","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab"}]},{"given":"Tasnima","family":"Sadekova","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab"}]},{"given":"Ivan","family":"Vovk","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab"}]}],"member":"263","reference":[{"journal-title":"Optimal Transport Old and New 338 of Grundlehren der Mathematischen Wissenschaften","year":"2016","author":"villani","key":"ref13"},{"key":"ref12","article-title":"Denoising Diffusion Implicit Models","author":"song","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.aml.2022.108225"},{"article-title":"Understanding DDPM Latent Codes Through Optimal Transport","year":"2022","author":"khrulkov","key":"ref14"},{"key":"ref11","article-title":"Analytic-DPM: An Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models","author":"bao","year":"2022","journal-title":"International Conference on Learning Representations"},{"article-title":"Gotta Go Fast When Generating Data with Score-Based Models","year":"2021","author":"jolicoeur-martineau","key":"ref10"},{"key":"ref2","article-title":"Score-Based Generative Modeling through Stochastic Differential Equations","author":"song","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref1","article-title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","author":"sohl-dickstein","year":"2015","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"key":"ref17","article-title":"Transfer Learning from Speaker Verification to Multispeaker Text-ToSpeech Synthesis","volume":"31","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"article-title":"Dual Diffusion Implicit Bridges for Image-toImage Translation","year":"2022","author":"su","key":"ref16"},{"key":"ref19","article-title":"Any-to-Many Voice Conversion With Location-Relative Sequence-toSequence Modeling","author":"liu","year":"2021","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92)","year":"2019","author":"yamagishi","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref25","article-title":"Crepe: A Convolutional Representation for Pitch Estimation","author":"kim","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref20","article-title":"TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer","author":"huang","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref22","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","author":"ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref21","article-title":"HiFiGAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Symbolic Music Generation with Diffusion Models","author":"mittal","year":"2021","journal-title":"Proceedings of the 22nd International Society for Music Information Retrieval Conference"},{"key":"ref7","article-title":"Grad-TTS: A Diffusion Probabilistic Model for Textto-Speech","author":"popov","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"ref9","article-title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","author":"popov","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref4","article-title":"Video Diffusion Models","author":"ho","year":"2022","journal-title":"ICLR Workshop on Deep Generative Models for Highly Structured Data"},{"key":"ref3","article-title":"Diffusion Models Beat GANs on Image Synthesis","author":"dhariwal","year":"2021","journal-title":"Advances in Neural IInformation Processing Systems"},{"article-title":"Diffusion models for Handwriting Generation","year":"2020","author":"luhman","key":"ref6"},{"article-title":"DreamFusion: Text-to-3D using 2D Diffusion","year":"2022","author":"poole","key":"ref5"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094854.pdf?arnumber=10094854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:29Z","timestamp":1700506649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094854","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}