{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T14:26:13Z","timestamp":1793629573107,"version":"4.5.1"},"reference-count":96,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100004504","name":"Lietuvos Mokslo Taryba","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004504","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":[[2026,11]]},"DOI":"10.1016\/j.jvoice.2024.07.016","type":"journal-article","created":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T17:29:38Z","timestamp":1722878978000},"page":"1739.e1-1739.e15","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"title":["Alaryngeal Speech Enhancement for Noisy Environments Using a Pareto Denoising Gated LSTM"],"prefix":"10.1016","volume":"40","author":[{"given":"Rytis","family":"Maskeli\u016bnas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robertas","family":"Dama\u0161evi\u010dius","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Audrius","family":"Kulikajevas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kipras","family":"Pribui\u0161is","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Virgilijus","family":"Uloza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2024.07.016_bib1","doi-asserted-by":"crossref","first-page":"18","DOI":"10.21147\/j.issn.1000-9604.2020.01.03","article-title":"Updates on larynx cancer epidemiology","volume":"32","author":"Nocini","year":"2020","journal-title":"Chin J Cancer Res"},{"key":"10.1016\/j.jvoice.2024.07.016_bib2","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.cden.2017.09.001","article-title":"Impact of oral cancer on quality of life","volume":"62","author":"Valdez","year":"2018","journal-title":"Dent Clin N Am"},{"key":"10.1016\/j.jvoice.2024.07.016_bib3","series-title":"Clinical Care and Rehabilitation in Head and Neck Cancer","first-page":"281","article-title":"Documenting voice and speech outcomes in alaryngeal speakers","author":"Doyle","year":"2019"},{"key":"10.1016\/j.jvoice.2024.07.016_bib4","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.otc.2022.11.003","article-title":"Voice restoration and quality of life in larynx cancer","volume":"56","author":"Tang","year":"2023","journal-title":"Otolaryngol Clin N Am"},{"key":"10.1016\/j.jvoice.2024.07.016_bib5","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1007\/s10772-020-09674-2","article-title":"Fundamentals, present and future perspectives of speech enhancement","volume":"24","author":"Das","year":"2020","journal-title":"Int J Speech Technol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib6","article-title":"Speech and language practitioners\u2019 experiences of commercially available voice-assisted technology: web-based survey study","volume":"9","author":"Kulkarni","year":"2022","journal-title":"JMIR Rehabilit Assist Technol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib7","doi-asserted-by":"crossref","DOI":"10.1002\/lio2.1212","article-title":"Factors associated with successful electrolarynx use after total laryngectomy, a multi-institutional study","volume":"9","author":"Pan","year":"2024","journal-title":"Laryngosc Invest Otolaryngol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib8","doi-asserted-by":"crossref","first-page":"20","DOI":"10.14639\/0392-100X-N2253","article-title":"Olfactory function in laryngectomised patients: tracheo-oesophageal versus oesophageal speech","volume":"43","author":"Bianco","year":"2023","journal-title":"Acta Otorhinolaryngol Ital"},{"key":"10.1016\/j.jvoice.2024.07.016_bib9","doi-asserted-by":"crossref","first-page":"2735","DOI":"10.1002\/hed.27506","article-title":"Protocolized awake secondary tracheoesophageal puncture with immediate voicing","volume":"45","author":"Jabbour","year":"2023","journal-title":"Head Neck"},{"key":"10.1016\/j.jvoice.2024.07.016_bib10","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2300255120","article-title":"Distributed feedforward and feedback cortical processing supports human speech production","volume":"120","author":"Wang","year":"2023","journal-title":"Proc Natl Acad Sci"},{"key":"10.1016\/j.jvoice.2024.07.016_bib11","doi-asserted-by":"crossref","first-page":"2386","DOI":"10.1109\/TASLP.2017.2740000","article-title":"Silent speech recognition as an alternative communication device for persons with laryngectomy","volume":"25","author":"Meltzner","year":"2017","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2024.07.016_bib12","doi-asserted-by":"crossref","first-page":"177995","DOI":"10.1109\/ACCESS.2020.3026579","article-title":"Silent speech interfaces for speech restoration: a review","volume":"8","author":"Gonzalez-Lopez","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2024.07.016_bib13","doi-asserted-by":"crossref","unstructured":"Pandey L, Hasan K, Arif AS. Acceptability of speech and silent speech input methods in private and public. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. ACM; 2021.","DOI":"10.1145\/3411764.3445430"},{"key":"10.1016\/j.jvoice.2024.07.016_bib14","series-title":"Clinical Care and Rehabilitation in Head and Neck Cancer","first-page":"129","article-title":"Elements of clinical training with the electrolarynx","author":"Nagle","year":"2019"},{"key":"10.1016\/j.jvoice.2024.07.016_bib15","doi-asserted-by":"crossref","first-page":"2386","DOI":"10.1109\/TASLP.2017.2740000","article-title":"Silent speech recognition as an alternative communication device for persons with laryngectomy","volume":"25","author":"Meltzner","year":"2017","journal-title":"IEEE\/ACM Transa Audio Speech Lang Process"},{"issue":"2S","key":"10.1016\/j.jvoice.2024.07.016_bib16","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1044\/2020_AJSLP-19-00201","article-title":"Respiratory\u2013swallow training methods: Accuracy of automated detection of swallow onset, respiratory phase, lung volume at swallow onset, and real-time performance feedback tested in healthy adults","volume":"29","author":"Hopkins-Rossabi","year":"2020","journal-title":"Am J Speech-Lang Pathol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib17","doi-asserted-by":"crossref","first-page":"66749","DOI":"10.1109\/ACCESS.2020.2985280","article-title":"A survey on signal processing based pathological voice detection techniques","volume":"8","author":"Islam","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2024.07.016_bib18","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s10772-018-09579-1","article-title":"Enhancement of esophageal speech obtained by a voice conversion technique using time dilated Fourier cepstra","volume":"22","author":"Othmane","year":"2018","journal-title":"Int J Speech Technol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib19","doi-asserted-by":"crossref","unstructured":"Dinh T, Kain A, Samlan R, et al. Increasing the intelligibility and naturalness of alaryngeal speech using voice conversion and synthetic fundamental frequency. In: Interspeech 2020. ISCA; 2020.","DOI":"10.21437\/Interspeech.2020-1196"},{"key":"10.1016\/j.jvoice.2024.07.016_bib20","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.neunet.2021.04.016","article-title":"FastTalker: a neural text-to-speech architecture with shallow and group autoregression","volume":"141","author":"Liu","year":"2021","journal-title":"Neural Netw"},{"key":"10.1016\/j.jvoice.2024.07.016_bib21","doi-asserted-by":"crossref","unstructured":"Serrano L, Raman S, Tavarez D, et al. Parallel vs. non-parallel voice conversion for esophageal speech. In: Interspeech 2019. ISCA; 2019.","DOI":"10.21437\/Interspeech.2019-2194"},{"key":"10.1016\/j.jvoice.2024.07.016_bib22","doi-asserted-by":"crossref","unstructured":"Doi H, Nakamura K, Toda T, et al. An evaluation of alaryngeal speech enhancement methods based on voice conversion techniques. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2011:5136\u20135139.","DOI":"10.1109\/ICASSP.2011.5947513"},{"key":"10.1016\/j.jvoice.2024.07.016_bib23","doi-asserted-by":"crossref","first-page":"537","DOI":"10.3390\/app13010537","article-title":"Mandarin electro-laryngeal speech enhancement using cycle-consistent generative adversarial networks","volume":"13","author":"Qian","year":"2022","journal-title":"Appl Sci"},{"key":"10.1016\/j.jvoice.2024.07.016_bib24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2738047","article-title":"Evaluation of a context-aware voice interface for ambient assisted living","volume":"7","author":"Vacher","year":"2015","journal-title":"ACM Trans Access Comput"},{"key":"10.1016\/j.jvoice.2024.07.016_bib25","doi-asserted-by":"crossref","unstructured":"Huq M. Enhancement of alaryngeal speech using generative adversarial network (GAN). In: Proceedings of IEEE\/ACS International Conference on Computer Systems and Applications. AICCSA; December 2021, vol 2021.","DOI":"10.1109\/AICCSA53542.2021.9686759"},{"key":"10.1016\/j.jvoice.2024.07.016_bib26","doi-asserted-by":"crossref","unstructured":"Huq M, Maskeliunas R. Speech enhancement using generative adversarial network (GAN), LNNS of Lecture Notes in Networks and Systems; 2022, vol 420.","DOI":"10.1007\/978-3-030-96305-7_26"},{"key":"10.1016\/j.jvoice.2024.07.016_bib27","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.compbiomed.2015.07.026","article-title":"Voice data mining for laryngeal pathology assessment","volume":"69","author":"Hemmerling","year":"2016","journal-title":"Comput Biol Med"},{"key":"10.1016\/j.jvoice.2024.07.016_bib28","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/3446776","article-title":"Understanding deep learning (still) requires rethinking generalization","volume":"64","author":"Zhang","year":"2021","journal-title":"Commun ACM"},{"key":"10.1016\/j.jvoice.2024.07.016_bib29","doi-asserted-by":"crossref","first-page":"3644","DOI":"10.3390\/cancers15143644","article-title":"Pareto-optimized non-negative matrix factorization approach to the cleaning of alaryngeal speech signals","volume":"15","author":"Maskeli\u016bnas","year":"2023","journal-title":"Cancers"},{"key":"10.1016\/j.jvoice.2024.07.016_bib30","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.specom.2017.01.008","article-title":"An overview of voice conversion systems","volume":"88","author":"Mohammadi","year":"2017","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2024.07.016_bib31","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1017\/S0022215111000910","article-title":"Effect of primary, cross-over, zigzag neopharyngoplasty on acoustic characteristics of alaryngeal, tracheoesophageal voice","volume":"125","author":"Albirmawy","year":"2011","journal-title":"J Laryngol Otol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib32","series-title":"Clinical Care and Rehabilitation in Head and Neck Cancer","first-page":"209","article-title":"Alaryngeal speech aerodynamics: lower and upper airway considerations","author":"Searl","year":"2019"},{"key":"10.1016\/j.jvoice.2024.07.016_bib33","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1044\/2016_JSLHR-S-16-0019","article-title":"The quantal larynx: the stable regions of laryngeal biomechanics and implications for speech production","volume":"60","author":"Moisik","year":"2017","journal-title":"J Speech Lang Hear Res"},{"key":"10.1016\/j.jvoice.2024.07.016_bib34","doi-asserted-by":"crossref","first-page":"192","DOI":"10.5507\/bp.2020.016","article-title":"Text-to-speech synthesis as an alternative communication means after total laryngectomy","volume":"165","author":"Repova","year":"2021","journal-title":"Biomed Pap"},{"key":"10.1016\/j.jvoice.2024.07.016_bib35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2019.01.007","article-title":"A network-modeling approach to investigating individual differences in articulatory-to-acoustic relationship strategies","volume":"108","author":"Carignan","year":"2019","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2024.07.016_bib36","first-page":"3155","article-title":"Role of multi-slice computed tomography and magnetic resonance imaging in evaluation of laryngeal tumors","volume":"86","author":"El-Arabawy","year":"2018","journal-title":"Med J Cairo Univ"},{"key":"10.1016\/j.jvoice.2024.07.016_bib37","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1044\/1058-0360(2011\/10-0066)","article-title":"Assessment of phonation threshold pressure: a critical review and clinical implications","volume":"20","author":"Plexico","year":"2011","journal-title":"Am J Speech-Lang Pathol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib38","doi-asserted-by":"crossref","first-page":"6","DOI":"10.4103\/2230-9748.141444","article-title":"Comparison of esophageal and tracheoesophageal speech modes in dual-mode alaryngeal speakers","volume":"4","author":"Maruthy","year":"2014","journal-title":"J Laryngol Voice"},{"key":"10.1016\/j.jvoice.2024.07.016_bib39","doi-asserted-by":"crossref","unstructured":"Doi H, Nakamura K, Toda T, et al. Statistical approach to enhancing esophageal speech based on Gaussian mixture models. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing; 2010:4250\u20134253.","DOI":"10.1109\/ICASSP.2010.5495676"},{"key":"10.1016\/j.jvoice.2024.07.016_bib40","doi-asserted-by":"crossref","unstructured":"Travieso CM, Alonso JB, Orozco-Arroyave JR, et al. Automatic detection of laryngeal pathologies in running speech based on the HMM transformation of the nonlinear dynamics. In: Advances in Nonlinear Speech Processing. Springer Berlin Heidelberg; 2013:136\u2013143.","DOI":"10.1007\/978-3-642-38847-7_18"},{"key":"10.1016\/j.jvoice.2024.07.016_bib41","series-title":"Lecture Notes on Data Engineering and Communications Technologies","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1007\/978-3-031-27762-7_7","article-title":"Predicted phase using deep neural networks to enhance esophageal speech","author":"Amarjouf","year":"2023"},{"key":"10.1016\/j.jvoice.2024.07.016_bib42","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1016\/j.bbe.2022.03.002","article-title":"Voice disorder classification using speech enhancement and deep learning models","volume":"42","author":"Chaiani","year":"2022","journal-title":"Biocybern Biomed Eng"},{"key":"10.1016\/j.jvoice.2024.07.016_bib43","doi-asserted-by":"crossref","first-page":"3415","DOI":"10.3390\/jcm9113415","article-title":"Convolutional neural network classifies pathological voice change in laryngeal cancer with high accuracy","volume":"9","author":"Kim","year":"2020","journal-title":"J Clin Med"},{"key":"10.1016\/j.jvoice.2024.07.016_bib44","article-title":"GBNF-VAE: a pathological voice enhancement model based on gold section for bottleneck feature with variational autoencoder","author":"Liu","year":"2023","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2024.07.016_bib45","doi-asserted-by":"crossref","unstructured":"Pascual S, Bonafonte A, Serr\u00e0 J, et al. Whispered-to-voiced alaryngeal speech conversion with generative adversarial networks; 2018.","DOI":"10.21437\/IberSPEECH.2018-25"},{"key":"10.1016\/j.jvoice.2024.07.016_bib46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2011\/289398","article-title":"Recurrent neural networks in computer-based clinical decision support for laryngopathies: an experimental study","volume":"2011","author":"Szko\u0142a","year":"2011","journal-title":"Comput Intell Neurosci"},{"key":"10.1016\/j.jvoice.2024.07.016_bib47","doi-asserted-by":"crossref","unstructured":"Serrano L, Tavarez D, Sarasola X et al. LSTM based voice conversion for laryngectomees. In: Proc. IberSPEECH 2018; 2018:122\u2013126.","DOI":"10.21437\/IberSPEECH.2018-26"},{"key":"10.1016\/j.jvoice.2024.07.016_bib48","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.3390\/app10041273","article-title":"An optimal feature parameter set based on gated recurrent unit recurrent neural networks for speech segment detection","volume":"10","author":"Dinler","year":"2020","journal-title":"Appl Sci"},{"key":"10.1016\/j.jvoice.2024.07.016_bib49","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1007\/s11277-022-09640-y","article-title":"Survey of deep learning paradigms for speech processing","volume":"125","author":"Bhangale","year":"2022","journal-title":"Wirel Pers Commun"},{"key":"10.1016\/j.jvoice.2024.07.016_bib50","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0227791","article-title":"Fully automatic segmentation of glottis and vocal folds in endoscopic laryngeal high-speed videos using a deep convolutional LSTM network","volume":"15","author":"Fehling","year":"2020","journal-title":"PLoS One"},{"key":"10.1016\/j.jvoice.2024.07.016_bib51","doi-asserted-by":"crossref","unstructured":"Kobayashi K, Toda T. Implementation of low-latency electrolaryngeal speech enhancement based on multi-task CLDNN. In: 2020 28th European Signal Processing Conference (EUSIPCO); 2021:396\u2013400.","DOI":"10.23919\/Eusipco47968.2020.9287721"},{"key":"10.1016\/j.jvoice.2024.07.016_bib52","doi-asserted-by":"crossref","unstructured":"Yen M-C, Huang W-C, Kobayashi K, et al. Mandarin electrolaryngeal speech voice conversion with sequence-to-sequence modeling. In: 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2021:650\u2013657.","DOI":"10.1109\/ASRU51503.2021.9687908"},{"key":"10.1016\/j.jvoice.2024.07.016_bib53","doi-asserted-by":"crossref","unstructured":"Wang Y, Skerry-Ryan RJ, Stanton D, et al. Tacotron: towards end-to-end speech synthesis; 2017.","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"10.1016\/j.jvoice.2024.07.016_bib54","doi-asserted-by":"crossref","unstructured":"Rekimoto J. WESPER: zero-shot and realtime whisper to normal voice conversion for whisper-based speech interactions. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. ACM; 2023.","DOI":"10.1145\/3544548.3580706"},{"key":"10.1016\/j.jvoice.2024.07.016_bib55","doi-asserted-by":"crossref","first-page":"2756","DOI":"10.1002\/lary.25454","article-title":"Speech-language pathology care and short- and long-term outcomes of laryngeal cancer treatment in the elderly","volume":"125","author":"Starmer","year":"2015","journal-title":"Laryngoscope"},{"key":"10.1016\/j.jvoice.2024.07.016_bib56","doi-asserted-by":"crossref","unstructured":"Petrushin VA, Tsirulnik LI, and Makarova V. Whispered speech prosody modeling for TTS synthesis. In: Proceedings of Speech Prosody 2010, Paper 288; 2010.","DOI":"10.21437\/SpeechProsody.2010-77"},{"key":"10.1016\/j.jvoice.2024.07.016_bib57","doi-asserted-by":"crossref","unstructured":"Boubakeur KN, Debyeche M, Amrouche A, et al. Prosodic modelling based speaker identification. In: 2022 2nd International Conference on New Technologies of Information and Communication (NTIC); 2022:1\u20136.","DOI":"10.1109\/NTIC55069.2022.10100506"},{"key":"10.1016\/j.jvoice.2024.07.016_bib58","doi-asserted-by":"crossref","first-page":"2483","DOI":"10.1587\/transinf.E93.D.2483","article-title":"HMM-based voice conversion using quantized f0 context","volume":"E93-D","author":"Nose","year":"2010","journal-title":"IEICE Trans Inform Syst"},{"key":"10.1016\/j.jvoice.2024.07.016_bib59","doi-asserted-by":"crossref","first-page":"4235","DOI":"10.3390\/electronics11244235","article-title":"A systematic review on machine learning techniques for early detection of mental, neurological and laryngeal disorders using patient\u2019s speech","volume":"11","author":"Sayadi","year":"2022","journal-title":"Electronics"},{"key":"10.1016\/j.jvoice.2024.07.016_bib60","doi-asserted-by":"crossref","unstructured":"\u0160imko J, Adigwe A, Suni A, et al. A hierarchical predictive processing approach to modelling prosody. In: SpeechProsody. ISCA; 2022.","DOI":"10.21437\/SpeechProsody.2022-86"},{"key":"10.1016\/j.jvoice.2024.07.016_bib61","doi-asserted-by":"crossref","first-page":"934.e17","DOI":"10.1016\/j.jvoice.2020.03.001","article-title":"The effects of contextual priming and alaryngeal speech mode on auditory-perceptual ratings of listener comfort","volume":"35","author":"Failla","year":"2021","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2024.07.016_bib62","doi-asserted-by":"crossref","first-page":"3188","DOI":"10.3390\/s22093188","article-title":"Implementing a statistical parametric speech synthesis system for a patient with laryngeal cancer","volume":"22","author":"Szklanny","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.jvoice.2024.07.016_bib63","doi-asserted-by":"crossref","DOI":"10.1016\/j.smhl.2021.100233","article-title":"VoiceLens: A multi-view multi-class disease classification model through daily-life speech data","volume":"23","author":"Bhattacharjee","year":"2022","journal-title":"Smart Health"},{"key":"10.1016\/j.jvoice.2024.07.016_bib64","doi-asserted-by":"crossref","unstructured":"Teplansky KJ, Wisler A, Cao B, et al. Tongue and lip motion patterns in alaryngeal speech. In: Proc. Interspeech 2020; 2020:4576\u20134580.","DOI":"10.21437\/Interspeech.2020-2854"},{"key":"10.1016\/j.jvoice.2024.07.016_bib65","doi-asserted-by":"crossref","unstructured":"Rekimoto J. DualVoice: speech interaction that discriminates between normal and whispered voice input. In: Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology. ACM; 2022.","DOI":"10.1145\/3526113.3545685"},{"key":"10.1016\/j.jvoice.2024.07.016_bib66","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1044\/1058-0360(2012\/12-0014)","article-title":"Evidence-based clinical voice assessment: a systematic review","volume":"22","author":"Roy","year":"2013","journal-title":"Am J Speech-Lang Pathol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib67","article-title":"Accuracy analysis of the multiparametric acoustic indices AVQI, ABI, and DSI for speech-language pathologist decision-making","author":"Penido","year":"2023","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2024.07.016_bib68","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1007\/s12070-022-03268-x","article-title":"Multidimensional voice assessment after management of early laryngeal cancer: a comparative study","volume":"75","author":"Hasanvand","year":"2022","journal-title":"Indian J Otolaryngol Head Neck Surg"},{"key":"10.1016\/j.jvoice.2024.07.016_bib69","doi-asserted-by":"crossref","first-page":"2366","DOI":"10.3390\/cancers14102366","article-title":"Lightweight deep learning model for assessment of substitution voicing and speech after laryngeal carcinoma surgery","volume":"14","author":"Maskeli\u016bnas","year":"2022","journal-title":"Cancers"},{"key":"10.1016\/j.jvoice.2024.07.016_bib70","doi-asserted-by":"crossref","first-page":"5363","DOI":"10.3390\/app13095363","article-title":"Pareto-optimized AVQI assessment of dysphonia: a clinical trial using various smartphones","volume":"13","author":"Maskeli\u016bnas","year":"2023","journal-title":"Appl Sci"},{"key":"10.1016\/j.jvoice.2024.07.016_bib71","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.1007\/s00405-020-06216-z","article-title":"Multidimensional evaluation of voice outcomes following total laryngectomy: a prospective multicenter cohort study","volume":"278","author":"van Sluis","year":"2020","journal-title":"Eur Arch Otorhinolaryngol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib72","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1007\/s00405-011-1900-8","article-title":"Voicing quantification is more relevant than period perturbation in substitution voices: an advanced acoustical study","volume":"269","author":"Dejonckere","year":"2012","journal-title":"Eur Arch Otorhinolaryngol"},{"key":"10.1016\/j.jvoice.2024.07.016_bib73","unstructured":"Boersma P, Weenink D. Praat: doing phonetics by computer (version 5.1.13); 2009."},{"key":"10.1016\/j.jvoice.2024.07.016_bib74","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.jvoice.2004.07.003","article-title":"Adverse effects of environmental noise on acoustic voice quality measurements","volume":"19","author":"Deliyski","year":"2005","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2024.07.016_bib75","unstructured":"Liu Z, Yu L, Xia G-S, et al. Mixed noise removal with Pareto prior. arXiv preprint arXiv:2008.11935; 2020."},{"key":"10.1016\/j.jvoice.2024.07.016_bib76","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/02699206.2022.2059398","article-title":"Substitution voicing index: towards improved speech assessment in patients who have undergone laryngeal oncosurgery","volume":"37","author":"Pribuisis","year":"2023","journal-title":"Clin Linguist Phon"},{"key":"10.1016\/j.jvoice.2024.07.016_bib77","doi-asserted-by":"crossref","first-page":"2366","DOI":"10.3390\/cancers14102366","article-title":"Lightweight deep learning model for assessment of substitution voicing and speech after laryngeal carcinoma surgery","volume":"14","author":"Maskeli\u016bnas","year":"2022","journal-title":"Cancers"},{"key":"10.1016\/j.jvoice.2024.07.016_bib78","unstructured":"Kingma DP, Ba J. A method for stochastic optimization; 2014."},{"key":"10.1016\/j.jvoice.2024.07.016_bib79","unstructured":"Loshchilov I, Hutter F. SGDR: stochastic gradient descent with warm restarts; 2016."},{"key":"10.1016\/j.jvoice.2024.07.016_bib80","doi-asserted-by":"crossref","first-page":"9748","DOI":"10.3390\/app12199748","article-title":"An artificial intelligence-based algorithm for the assessment of substitution voicing","volume":"12","author":"Uloza","year":"2022","journal-title":"Appl Sci"},{"key":"10.1016\/j.jvoice.2024.07.016_bib81","doi-asserted-by":"crossref","first-page":"3661","DOI":"10.1002\/sim.2832","article-title":"Chi-squared and Fisher\u2013Irwin tests of two-by-two tables with small sample recommendations","volume":"26","author":"Campbell","year":"2007","journal-title":"Stat Med"},{"key":"10.1016\/j.jvoice.2024.07.016_bib82","doi-asserted-by":"crossref","unstructured":"Pascual S, Bonafonte A, Serr\u00e0 J, et al. Whispered-to-voiced alaryngeal speech conversion with generative adversarial networks; 2018.","DOI":"10.21437\/IberSPEECH.2018-25"},{"key":"10.1016\/j.jvoice.2024.07.016_bib83","doi-asserted-by":"crossref","unstructured":"Kong Z, Ping W, Dantrey A, et al. Speech denoising in the waveform domain with self-attention. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2022:7867\u20137871.","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"10.1016\/j.jvoice.2024.07.016_bib84","doi-asserted-by":"crossref","unstructured":"Fu S-W, Yu C, Hsieh T-A,\u00a0et al. .Metricgan+: An improved version of metricgan for speech enhancement, 2021.","DOI":"10.21437\/Interspeech.2021-599"},{"key":"10.1016\/j.jvoice.2024.07.016_bib85","doi-asserted-by":"crossref","first-page":"1700","DOI":"10.1109\/LSP.2020.3025020","article-title":"Improving GANs for speech enhancement","volume":"27","author":"Phan","year":"2020","journal-title":"IEEE Signal Process Lett"},{"key":"10.1016\/j.jvoice.2024.07.016_bib86","doi-asserted-by":"crossref","first-page":"1404","DOI":"10.1109\/TASLP.2020.2987441","article-title":"Deepmmse: a deep learning approach to MMSE-based noise power spectral density estimation","volume":"28","author":"Zhang","year":"2020","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2024.07.016_bib87","doi-asserted-by":"crossref","unstructured":"Defossez A, Synnaeve G, and Adi Y. Real time speech enhancement in the waveform domain; 2020.","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"10.1016\/j.jvoice.2024.07.016_bib88","doi-asserted-by":"crossref","unstructured":"Rethage D, Pons J, Serra X. A wavenet for speech denoising. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2018:5069\u20135073.","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"10.1016\/j.jvoice.2024.07.016_bib89","unstructured":"Latif S, Rana R, Khalifa S, et al. Deep representation learning in speech processing: challenges, recent advances, and future trends. arXiv preprint arXiv:2001.00378; 2020."},{"key":"10.1016\/j.jvoice.2024.07.016_bib90","doi-asserted-by":"crossref","first-page":"1369","DOI":"10.1109\/TASLP.2018.2825108","article-title":"Online, loudness-invariant vocal detection in mixed music signals","volume":"26","author":"Lehner","year":"2018","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2024.07.016_bib91","doi-asserted-by":"crossref","first-page":"235","DOI":"10.2478\/jaiscr-2019-0006","article-title":"Performance evaluation of deep neural networks applied to speech recognition: RNN, LSTM and GRU","volume":"9","author":"Shewalkar","year":"2019","journal-title":"J Artif Intell Soft Comput Res"},{"key":"10.1016\/j.jvoice.2024.07.016_bib92","doi-asserted-by":"crossref","unstructured":"Sun L, Du J, Dai L-R, et al. Multiple-target deep learning for LSTM-RNN based speech enhancement. In: 2017 Hands-free Speech Communications and Microphone Arrays (HSCMA). IEEE; 2017:136\u2013140.","DOI":"10.1109\/HSCMA.2017.7895577"},{"key":"10.1016\/j.jvoice.2024.07.016_bib93","doi-asserted-by":"crossref","first-page":"24350","DOI":"10.1109\/ACCESS.2021.3056711","article-title":"Towards more efficient DNN-based speech enhancement using quantized correlation mask","volume":"9","author":"Abdullah","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2024.07.016_bib94","doi-asserted-by":"crossref","first-page":"2460","DOI":"10.1109\/TASLP.2018.2867947","article-title":"DNN-supported speech enhancement with cepstral estimation of both excitation and envelope","volume":"26","author":"Elshamy","year":"2018","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jvoice.2024.07.016_bib95","doi-asserted-by":"crossref","first-page":"2244","DOI":"10.1121\/1.5031112","article-title":"Speech enhancement for cochlear implant recipients","volume":"143","author":"Wang","year":"2018","journal-title":"J Acoust Soc Am"},{"key":"10.1016\/j.jvoice.2024.07.016_bib96","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1111\/1460-6984.12802","article-title":"Communication competence and disability secondary to laryngectomy and tracheoesophageal puncture voice restoration","volume":"58","author":"Doyle","year":"2023","journal-title":"Int J Lang Commun Disord"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199724002285?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199724002285?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T13:28:46Z","timestamp":1793626126000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199724002285"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":96,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["S0892199724002285"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2024.07.016","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Alaryngeal Speech Enhancement for Noisy Environments Using a Pareto Denoising Gated LSTM","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2024.07.016","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Inc. on behalf of The Voice Foundation.","name":"copyright","label":"Copyright"}]}}