{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T22:42:05Z","timestamp":1792276925671,"version":"4.4.0"},"reference-count":46,"publisher":"Elsevier BV","issue":"5","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271344"],"award-info":[{"award-number":["62271344"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019062","name":"Tianjin Research Innovation Project for Postgraduate Students","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019062","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","jvoice.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Voice"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1016\/j.jvoice.2023.03.012","type":"journal-article","created":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T01:01:33Z","timestamp":1683680493000},"page":"1171-1182","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["GBNF-VAE: A Pathological Voice Enhancement Model Based on Gold Section for Bottleneck Feature With Variational Autoencoder"],"prefix":"10.1016","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3919-5370","authenticated-orcid":false,"given":"Ganjun","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2317-644X","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biyun","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dehui","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2023.03.012_bib0001","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1109\/TASLP.2020.3036783","article-title":"A cross-entropy-guided measure (CEGM) for assessing speech recognition performance and optimizing DNN-based speech enhancement","volume":"29","author":"Chai","year":"2021","journal-title":"IEEE ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0002","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1109\/TASLP.2020.2986877","article-title":"Multi-level single channel speech enhancement using a unified framework for estimating magnitude and phase spectra","volume":"28","author":"Lavanya","year":"2020","journal-title":"IEEE ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0003","doi-asserted-by":"crossref","first-page":"2150","DOI":"10.1109\/TASLP.2019.2937174","article-title":"Binaural codebook-based speech enhancement with atomic speech presence probability","volume":"27","author":"Wood","year":"2019","journal-title":"IEEE ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0004","first-page":"1263","article-title":"The application of deep neural network in speech enhancement processing","author":"Chen","year":"2018","journal-title":"2018 5th International Conference on Information Science and Control Engineering (ICISCE)"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0005","first-page":"1070","article-title":"Joint optimization of modified ideal radio mask and deep neural networks for monaural speech enhancement","author":"Han","year":"2017","journal-title":"2017 IEEE 9th International Conference on Communication Software and Networks (ICCSN)"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0006","doi-asserted-by":"crossref","first-page":"2696","DOI":"10.21437\/Interspeech.2021-859","article-title":"Single-channel speech enhancement using learnable loss mixup","author":"Chang","year":"2021","journal-title":"Proc Interspeech 2021"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0007","first-page":"136","article-title":"Glottal source modeling in dysphonic speech","volume":"113","author":"Roy","year":"2019","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0008","first-page":"1","article-title":"Artificial neural network based voice pathology detection using time-domain features","volume":"109","author":"Eraslan","year":"2021","journal-title":"Appl Soft Comput"},{"issue":"4","key":"10.1016\/j.jvoice.2023.03.012_bib0009","first-page":"2373","article-title":"A pilot study of pink noise therapy for improving speech in Parkinson\u2019s disease","volume":"141","author":"Meltzner","year":"2017","journal-title":"J Acoust Soc Am"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0010","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.jbi.2018.07.014","article-title":"Relief-based feature selection: Introduction and review","volume":"85","author":"Urbanowicz","year":"2018","journal-title":"J Biomed Inf"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0011","article-title":"Streaming feature selection algorithms for big data: a survey","author":"AlNuaimi","year":"2019","journal-title":"Appl Comput Inf"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0012","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.compeleceng.2013.11.024","article-title":"A survey on feature selection methods","volume":"1","author":"Chandrashekar","year":"2014","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0013","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1007\/s10772-012-9186-9","article-title":"MCRA noise estimation for KLT-VRE-based speech enhancement","volume":"16","author":"Saadoune","year":"2013","journal-title":"Int J Speech Technol"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0014","doi-asserted-by":"crossref","first-page":"1608","DOI":"10.1109\/TASLP.2020.2996503","article-title":"A multi-target SNR-progressive learning approach to regression based speech enhancement","volume":"28","author":"Tu","year":"2020","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"2","key":"10.1016\/j.jvoice.2023.03.012_bib0015","first-page":"234","article-title":"Gold section search algorithm for maximizing an object-oriented neural network-based cost function","volume":"29","author":"Bhatt","year":"1999","journal-title":"IEEE Trans Syst Man Cybern Part C (Appl Rev)"},{"issue":"6","key":"10.1016\/j.jvoice.2023.03.012_bib0016","first-page":"1717","article-title":"A new thresholding method based on the gold section search for image segmentation","volume":"20","author":"Lu","year":"2011","journal-title":"IEEE Trans Image Process"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0017","first-page":"355","article-title":"Application of golden section search for optimization of fractal antenna design","volume":"126","author":"Chakraborty","year":"2012","journal-title":"Progr Electromagnet Res"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0018","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.anl.2020.08.026","article-title":"Surgical effects of type-I thyroplasty and fat injection laryngoplasty on voice recovery","volume":"48","author":"Hasukawa","year":"2021","journal-title":"Auris Nasus Larynx"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0019","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1111\/j.1365-2273.1994.tb01234.x","article-title":"Communication, functional disorders and lifestyle changes after total laryngectomy","volume":"19","author":"Ackerstaff","year":"1994","journal-title":"Clin Otolaryngol"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0020","series-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing","first-page":"4874","article-title":"Speaker verification using neural embedding of phonetic posterior features","author":"Snyder","year":"2018"},{"issue":"9","key":"10.1016\/j.jvoice.2023.03.012_bib0021","first-page":"1353","article-title":"Robust speaker recognition in noisy environments using convolutional neural networks","volume":"25","author":"Yousefi","year":"2018","journal-title":"IEEE Signal Process Lett"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0022","series-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing","article-title":"Robust speaker recognition using attention-based deep neural networks","author":"Liu","year":"2019"},{"issue":"2","key":"10.1016\/j.jvoice.2023.03.012_bib0023","first-page":"364","article-title":"Speaker recognition in adverse conditions using deep neural networks trained on synthetic noisy speech","volume":"13","author":"Liu","year":"2019","journal-title":"IEEE J Select Topics Signal Process"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0024","doi-asserted-by":"crossref","first-page":"1940","DOI":"10.1109\/JBHI.2020.2978103","article-title":"Multiple vowels repair based on pitch extraction and line spectrum pair feature for voice disorder","volume":"24","author":"Zhang","year":"2020","journal-title":"IEEE J Biomed Health Inf"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0025","doi-asserted-by":"crossref","first-page":"93","DOI":"10.3844\/ajassp.2012.93.102","article-title":"An improved time domain pitch detection algorithm for pathological voice","volume":"9","author":"Jamaludin","year":"2012","journal-title":"Am J Appl Sci"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0026","article-title":"PVR-AFM: a pathological voice repair system based on non-linear structure","author":"Zhang","year":"2021","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0027","first-page":"107","article-title":"Methods for formant extraction in speech of patients after total laryngectomy","volume":"1","author":"Pietruch","year":"2006","journal-title":"IEEE J Biomed Health Inf"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0028","first-page":"93","article-title":"Correlation between vocal function and quantitative videofluoroscopic analysis of swallowing in patients with vocal cord paralysis","volume":"116","author":"Lee","year":"2007","journal-title":"Ann Otol Rhinol Laryngol"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0029","first-page":"835","article-title":"Vocal fold polyps and their impact on the glottal airflow: an experimental study","volume":"114","author":"Hofheinz","year":"2005","journal-title":"Ann Otol Rhinol Laryngol"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0030","first-page":"401","article-title":"Visual assessment of laryngeal airflow in speech pathology","volume":"35","author":"Story","year":"2000","journal-title":"Int J Lang Commun Disord"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0031","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1109\/ICASSP.1979.1170788","article-title":"Enhancement of speech corrupted by acoustic noise","volume":"4","author":"Berouti","year":"1979","journal-title":"Proc Int Conf Acoust Speech Signal Process (ICASS)"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0032","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1109\/TASSP.1978.1163086","article-title":"All-pole modeling of degraded speech","volume":"26","author":"Lim","year":"1978","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0033","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1109\/5.168664","article-title":"Statistical-model-based speech enhancement systems","volume":"80","author":"Ephraim","year":"1992","journal-title":"Proc IEEE"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0034","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/0167-6393(91)90027-Q","article-title":"Speech enhancement from noise: a regenerative approach","volume":"10","author":"Dendrinos","year":"1991","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0035","first-page":"553","article-title":"Noise reduction using connectionist models","author":"Tamura","year":"1988","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0036","first-page":"733","article-title":"Speech enhancement with missing data techniques using recurrent neural networks","author":"Parveen","year":"2004","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0037","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"Lu","year":"2013","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0038","first-page":"71","article-title":"Recurrent deep stacking networks for supervised speech separation","author":"Wang","year":"2017","journal-title":"IEEE Int Conf Acoust Speech Signal Process"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0039","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/WASPAA.2019.8937189","article-title":"A perceptual weighting filter loss for DNN training in speech enhancement","author":"Zhao","year":"2019","journal-title":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0040","first-page":"1273","article-title":"Learning latent representations for speech generation and transformation","author":"Hsu","year":"2017","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0041","doi-asserted-by":"crossref","first-page":"1770","DOI":"10.21437\/Interspeech.2016-1183","article-title":"Modeling and transforming speech using variational autoencoders","author":"Blaauw","year":"2016","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0042","doi-asserted-by":"crossref","unstructured":"Bando Y, Mimura M, Itoyama K, Yoshii K, Kawahara T. Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, 2018, pp. 716\u2013720.","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0043","series-title":"English Multi-Peaker Corpus for CSTR Voice Cloning Toolkit[J]","author":"Veaux","year":"2017"},{"issue":"3","key":"10.1016\/j.jvoice.2023.03.012_bib0044","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","article-title":"Noisex-92: A database and an experiment to study the effect of additive noise on speech recognition systems[J]","volume":"12","author":"Varga","year":"1993","journal-title":"Speech communication"},{"key":"10.1016\/j.jvoice.2023.03.012_bib0045","unstructured":"Barry WJ, Ptzer M. Saarbrucken voice database. Institute of Phonetics, Universitt des Saarlandes; 2007. http:\/\/www.stimmdatenbank.coli.uni-saarland.de."},{"key":"10.1016\/j.jvoice.2023.03.012_bib0046","unstructured":"Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv:141269802014."}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199723001054?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199723001054?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T22:39:15Z","timestamp":1792276755000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199723001054"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":46,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["S0892199723001054"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2023.03.012","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"GBNF-VAE: A Pathological Voice Enhancement Model Based on Gold Section for Bottleneck Feature With Variational Autoencoder","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2023.03.012","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 The Voice Foundation. Published by Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}