{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:27:03Z","timestamp":1747200423081,"version":"3.28.0"},"reference-count":28,"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\/icassp49357.2023.10094872","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":4,"title":["Embedding a Differentiable Mel-Cepstral Synthesis Filter to a Neural Speech Synthesis System"],"prefix":"10.1109","author":[{"given":"Takenori","family":"Yoshimura","sequence":"first","affiliation":[{"name":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Takaki","sequence":"additional","affiliation":[{"name":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Nakamura","sequence":"additional","affiliation":[{"name":"Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiichiro","family":"Oura","sequence":"additional","affiliation":[{"name":"Techno-Speech, Inc.,Department of Research and Development,Nagoya,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukiya","family":"Hono","sequence":"additional","affiliation":[{"name":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihiko","family":"Nankaku","sequence":"additional","affiliation":[{"name":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiichi","family":"Tokuda","sequence":"additional","affiliation":[{"name":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"4215","article-title":"Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis","author":"tokuda","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3118033"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/89.482216"},{"key":"ref14","first-page":"5640","article-title":"Directly modeling voiced and unvoiced components in speech waveforms by neural networks","author":"tokuda","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3061245"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(86)90008-7"},{"key":"ref1","first-page":"1229","article-title":"Statistical parametric speech synthesis","volume":"4","author":"black","year":"2007","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref17","article-title":"DDSP: Differentiable digital signal processing","author":"engel","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902701"},{"article-title":"Differentiable WORLD synthesizer-based neural vocoder with application to end-to-end audio style transfer","year":"2022","author":"nercessian","key":"ref19"},{"article-title":"Speech synthesis and control using differentiable DSP","year":"2020","author":"fabbro","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-6"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3104165"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/ecjc.4430760204"},{"journal-title":"Discrete-Time Signal Processing","year":"2009","author":"oppenheim","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1972.8727"},{"key":"ref28","first-page":"7239","article-title":"Fast and high-quality singing voice synthesis system based on convolutional neural networks","author":"nakamura","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","year":"2021","author":"kim","key":"ref27"},{"key":"ref8","first-page":"17022","article-title":"HiFi-GAN: 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":"ref7","first-page":"6199","article-title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","author":"yamamoto","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref9","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2020","journal-title":"2009 00713"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref3","first-page":"11","article-title":"Mel log spectrum approximation (MLSA) filter for speech synthesis","volume":"66","author":"imai","year":"1983","journal-title":"Electronics and Communications in Japan"},{"key":"ref6","first-page":"5891","article-title":"LPCNet: Improving neural speech synthesis through linear prediction","author":"valin","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","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\/10094872.pdf?arnumber=10094872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:03Z","timestamp":1700507283000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094872","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}