{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:06:05Z","timestamp":1730297165841,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022757","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"955-961","source":"Crossref","is-referenced-by-count":0,"title":["SIMD-Size Aware Weight Regularization for Fast Neural Vocoding on CPU"],"prefix":"10.1109","author":[{"given":"Hiroki","family":"Kanagawa","sequence":"first","affiliation":[{"name":"NTT Corporation"}]},{"given":"Yusuke","family":"Ijima","sequence":"additional","affiliation":[{"name":"NTT Corporation"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269005"},{"key":"ref15","article-title":"Pruning filters for efficient convnets","author":"li","year":"2017","journal-title":"Proc ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1642"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053991"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053337"},{"key":"ref2","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"9","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref1","article-title":"WaveNet: A generative model for raw audio","volume":"abs 1609 3499","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref17","first-page":"1091","article-title":"Sparse activity and sparse connectivity in supervised learning","volume":"14","author":"thom","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","article-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","author":"zhu","year":"2018","journal-title":"Proc ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747898"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.02.029"},{"key":"ref24","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref26","first-page":"3391","article-title":"Aligned weight regularizers for pruning pretrained neu-ral networks","author":"neill","year":"2022","journal-title":"Proc ACL"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10556"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683791"},{"key":"ref22","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"Proc ICLR"},{"key":"ref21","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2020","journal-title":"Proc ICLR"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref27","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc ICML"},{"key":"ref8","first-page":"2410","article-title":"Efficient Neural Audio Synthesis","volume":"80","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref7","article-title":"HiFiGAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref4","first-page":"3617","article-title":"WaveGlow: A flow-based generative network for speech synthesis","author":"catanzaro","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref3","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLR"},{"key":"ref6","article-title":"Me1GAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022757.pdf?arnumber=10022757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:33Z","timestamp":1676912913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022757\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022757","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}