{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:03:58Z","timestamp":1764403438454,"version":"3.33.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848612","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Gamma-VAE: Speech representation based on VAE assuming gamma distribution for both latent variables and observation"],"prefix":"10.1109","author":[{"given":"Nanako","family":"Imaichi","sequence":"first","affiliation":[{"name":"University of Electro-Communication,Chofu, Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toru","family":"Nakashika","sequence":"additional","affiliation":[{"name":"University of Electro-Communication,Chofu, Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"article-title":"Auto-Encoding Variational Bayes","volume-title":"Proceedings of the 2nd International Conference on Learning Representations","author":"Diederik P Kingma","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref5","first-page":"2672","article-title":"Generative adversarial net","volume-title":"Proc. NIPS 2014","author":"Goodfellow"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_7"},{"key":"ref7","first-page":"3483","article-title":"Learnig structured output representation using deep conditional generative models","author":"shon","year":"2015"},{"key":"ref8","article-title":"Neural Discrete Representation Learning","author":"van den Oord Oriol Vinyals","year":"2017","journal-title":"Advances in Neural Information Process- ing Systems (NIPS) CoRR, abs\/1711.00937"},{"key":"ref9","first-page":"1","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume":"32","author":"van den Oord A","year":"2019","journal-title":"Advances in Neural Information Process-ing Systems (NIPS)"},{"article-title":"SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization","year":"2022","author":"Takida","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095656"},{"key":"ref12","first-page":"161","article-title":"Drum score estimation for musical acoustic signals using NMF with VAE as a prior distribution","volume":"1","author":"Yoshiaki","year":"2018","journal-title":"Collection of Lectures at the 80th National Convention"},{"key":"ref13","first-page":"1","article-title":"Robust probability density estimation by Student-t VAE","volume":"36","author":"HiroshiIwata","year":"2021","journal-title":"Transactions of the Japanese Society for Artificial Intelligence"},{"key":"ref14","first-page":"489","article-title":"Reparameterization gradients through acceptance-rejection sampling algorithms","volume-title":"Proc. Artificial Intelligence and Statistics","volume":"54","author":"Naesseth"},{"article-title":"Implicit reparameterization gradients. advances in neural information processing systems","volume-title":"Proc. NeurIPS","author":"Figurnov","key":"ref15"},{"key":"ref16","first-page":"186","article-title":"An application of the principle of maximum information preservation to linear systems","volume":"1","author":"Linske","year":"1989","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"2","article-title":"Elbo surgery: Yet another way to carve up the variational evidence lower bound","volume-title":"Workshop in Advances in Approximate Bayesian Inferenc","volume":"1","author":"Hoffman"},{"key":"ref18","first-page":"299","article-title":"Information type measures of difference of probability dis- tributions and indirect observations","volume":"2","author":"Csisza","year":"1967","journal-title":"Stud. Sci. Math. Hung."},{"key":"ref19","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"Lee","year":"2001","journal-title":"IAdvances in neural information processing systems"},{"article-title":"\u03b2-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"International conference on learning representations","author":"Higgins","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref22","first-page":"1","article-title":"Phase Recovery from Amplitude Spectrograms Based on von Mises Distribution DNN","volume":"54","author":"Tkaamichi","year":"2012","journal-title":"IPSJ Research Report"},{"article-title":"WaveNet: A Generative Model for Raw Audio","year":"2016","author":"van den Oord","key":"ref23"},{"key":"ref24","first-page":"17022","article-title":"HiFi-GAN: generative adver- sarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"K"},{"key":"ref25","first-page":"357","article-title":"Multi-lingual Corpora for Speech-to-Speech Translation Research","volume":"2","author":"Takezawa","year":"2004","journal-title":"ICSLP"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848612.pdf?arnumber=10848612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:08:14Z","timestamp":1738044494000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848612","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}