{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T14:57:52Z","timestamp":1787237872509,"version":"build-2736575974"},"reference-count":58,"publisher":"Acoustical Society of America (ASA)","issue":"4","license":[{"start":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T00:00:00Z","timestamp":1744934400000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014437","name":"Wenner-Gren Stiftelserna","doi-asserted-by":"publisher","award":["GFOh2018-0014"],"award-info":[{"award-number":["GFOh2018-0014"]}],"id":[{"id":"10.13039\/100014437","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202006010113"],"award-info":[{"award-number":["202006010113"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,1]]},"abstract":"<jats:p>The electroglottographic (EGG) signal offers a non-invasive approach to analyze phonation. It is known, if not obvious, that the onset of vocal fold contacting has a substantial effect on how the vocal folds vibrate and on the quality of the voice. Given that the presence or absence of vocal fold contacting has major consequences also for the interpretation of acoustic metrics, it is compelling to consider the possibility of predicting EGG signals directly from the microphone speech signal. This retrospective study presents a neural network model for EGG signal estimation utilizing a WaveNet architecture augmented with a self-attention mechanism. The model was trained on an existing dataset that comprehensively recorded participants' full voice range. The proposed model effectively captures the temporal dynamics and morphological characteristics of normophonic EGG waveforms, achieving outputs that closely resemble the ground truth in terms of EGG waveshape and extracted EGG metrics. For evaluation, voice mapping was used to display the distribution similarities of extracted metrics from predicted and ground truth EGG waveforms. The model exhibits proficiency in accurately estimating EGG signals in areas of stable and contacting voicing but displays reduced accuracy in transitional and breathy phonatory conditions.<\/jats:p>","DOI":"10.1121\/10.0036514","type":"journal-article","created":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T08:15:04Z","timestamp":1744964104000},"page":"3033-3044","update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":2,"title":["A WaveNet-based model for predicting the electroglottographic signal from the acoustic voice signal"],"prefix":"10.1121","volume":"157","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0700-7216","authenticated-orcid":false,"given":"Huanchen","family":"Cai","sequence":"first","affiliation":[{"name":"Division of Speech, Music and Hearing, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology , SE-100 44 Stockholm,","place":["Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3362-7518","authenticated-orcid":false,"given":"Sten","family":"Ternstr\u00f6m","sequence":"additional","affiliation":[{"name":"Division of Speech, Music and Hearing, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology , SE-100 44 Stockholm,","place":["Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"231","published-online":{"date-parts":[[2025,4,18]]},"reference":[{"key":"2025041808144826300_c1","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1007\/s12046-011-0041-5","article-title":"Glottal inverse filtering analysis of human voice production: A review of estimation and parameterization methods of the glottal excitation and their applications","volume":"36","year":"2011","journal-title":"Sadhana"},{"key":"2025041808144826300_c2","first-page":"6739","article-title":"GCI detection from raw speech using a fully-convolutional network","year":"2020"},{"key":"2025041808144826300_c3","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/S0892-1997(05)80123-7","article-title":"Electroglottography","volume":"6","year":"1992","journal-title":"J. Voice"},{"key":"2025041808144826300_c4","first-page":"401","article-title":"Semi-supervised learning of glottal pulse positions in a neural analysis-synthesis framework","year":"2021"},{"key":"2025041808144826300_c5","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1037\/0735-7036.109.4.398","article-title":"Modes of vocal variation in Sykes's monkey (Cercopithecus albogularis) squeals","volume":"109","year":"1995","journal-title":"J. Comp. Psychol."},{"key":"2025041808144826300_c6","doi-asserted-by":"publisher","first-page":"12092","DOI":"10.3390\/app122312092","article-title":"Mapping phonation types by clustering of multiple metrics","volume":"12","year":"2022","journal-title":"Appl. Sci."},{"key":"2025041808144826300_c7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2024.03.012","article-title":"Effects on voice quality of thyroidectomy: A qualitative and quantitative study using voice maps","year":"2024","journal-title":"J. Voice"},{"key":"2025041808144826300_c8","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/S0892-1997(99)80063-0","article-title":"A study of the effectiveness of voice therapy in the treatment of 45 patients with nonorganic dysphonia","volume":"13","year":"1999","journal-title":"J. Voice"},{"key":"2025041808144826300_c9","first-page":"1909","article-title":"IVAE: An improved deep learning structure for EEG signal characterization and reconstruction","year":"2020"},{"key":"2025041808144826300_c10","volume-title":"Speech Processing and Synthesis Toolboxes","year":"2000"},{"key":"2025041808144826300_c12","doi-asserted-by":"publisher","first-page":"Cd012483","DOI":"10.1002\/14651858.CD012483.pub2","article-title":"Intraoperative neuromonitoring versus visual nerve identification for prevention of recurrent laryngeal nerve injury in adults undergoing thyroid surgery","volume":"1","year":"2019","journal-title":"Cochrane Database Syst. Rev."},{"key":"2025041808144826300_c13","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/S0892-1997(05)80077-3","article-title":"Problems and pitfalls of electroglottography","volume":"4","year":"1990","journal-title":"J. Voice"},{"key":"2025041808144826300_c14","first-page":"5946","article-title":"Glottal instants extraction from speech signal using generative adversarial network","year":"2019"},{"key":"2025041808144826300_c15","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1097\/MOO.0b013e3283395dd4","article-title":"State of the art laryngeal imaging: Research and clinical implications","volume":"18","year":"2010","journal-title":"Curr. Opin. Otolaryngol. Head Neck Surg."},{"key":"2025041808144826300_c16","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1109\/JBHI.2017.2654683","article-title":"Effective glottal instant detection and electroglottographic parameter extraction for automated voice pathology assessment","volume":"22","year":"2018","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"2025041808144826300_c17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2023.03.018","article-title":"Classification of speaking and singing voices using bioimpedance measurements and deep learning","year":"2023","journal-title":"J. Voice"},{"key":"2025041808144826300_c18","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1109\/TASL.2011.2170835","article-title":"Detection of glottal closure instants from speech signals: A quantitative review","volume":"20","year":"2012","journal-title":"IEEE Trans. Audio. Speech Lang. Process."},{"key":"2025041808144826300_c19","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1016\/j.jvoice.2009.05.003","article-title":"High-speed imaging and electroglottography measurements of the open quotient in untrained male voices' register transitions","volume":"24","year":"2010","journal-title":"J. Voice"},{"key":"2025041808144826300_c20","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1017\/S0025100300002796","article-title":"Laryngographic study of phonation type and laryngeal configuration","volume":"14","year":"1984","journal-title":"J. Int. Phonetic Assoc."},{"key":"2025041808144826300_c21","year":"1960"},{"key":"2025041808144826300_c22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1163\/19606028-04601001","article-title":"Phonetic and phonological properties of tones in Shanghai Chinese","volume":"46","year":"2017","journal-title":"Cah. Linguist. Asie Orient."},{"key":"2025041808144826300_c23","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.specom.2011.08.003","article-title":"Data-driven voice source waveform analysis and synthesis","volume":"54","year":"2012","journal-title":"Speech Commun."},{"key":"2025041808144826300_c24","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.jvoice.2015.03.018","article-title":"Relationship between the electroglottographic signal and vocal fold contact area","volume":"30","year":"2016","journal-title":"J. Voice"},{"key":"2025041808144826300_c25","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.1121\/1.1646401","article-title":"On the use of the derivative of electroglottographic signals for characterization of nonpathological phonation","volume":"115","year":"2004","journal-title":"J. Acoust. Soc. Am."},{"key":"2025041808144826300_c26","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/j.jvoice.2018.12.014","article-title":"Electroglottography: An update","volume":"34","year":"2020","journal-title":"J. Voice"},{"key":"2025041808144826300_c27","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.jvoice.2018.01.003","article-title":"Fundamental frequency estimation of low-quality electroglottographic signals","volume":"33","year":"2019","journal-title":"J. Voice"},{"key":"2025041808144826300_c28","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1080\/14015430500376580","article-title":"A comparison of different methods to measure the EGG contact quotient","volume":"31","year":"2006","journal-title":"Logopedics Phoniatrics Vocol."},{"key":"2025041808144826300_c29","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1097\/00020840-199706000-00005","article-title":"Current diagnostics and office practice: Appropriate use of objective measures of vocal function in the multidisciplinary management of voice disorders","volume":"5","year":"1997","journal-title":"Curr. Opin. Otolaryngol. Head Neck Surg."},{"key":"2025041808144826300_c30","article-title":"Machine learning analysis of speech and EGG for the diagnosis of voice pathology","year":"2021"},{"key":"2025041808144826300_c31","doi-asserted-by":"publisher","first-page":"100074","DOI":"10.1016\/j.cmpbup.2022.100074","article-title":"Voice pathology detection using convolutional neural networks with electroglottographic (EGG) and speech signals","volume":"2","year":"2022","journal-title":"Comput. Methods Programs Biomed. Update"},{"key":"2025041808144826300_c32","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1044\/1058-0360(2008\/08-0017)","article-title":"Consensus auditory-perceptual evaluation of voice: Development of a standardized clinical protocol","volume":"18","year":"2009","journal-title":"Am. J. Speech. Lang. Pathol."},{"key":"2025041808144826300_c33","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/978-3-031-20650-4","article-title":"Sequence-to-sequence CNN-BILSTM based glottal closure instant detection from raw speech","volume-title":"Artificial Neural Networks in Pattern Recognition","author":"El Gayar","year":"2023"},{"key":"2025041808144826300_c34","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/TASL.2006.876878","article-title":"Estimation of glottal closure instants in voiced speech using the DYPSA algorithm","volume":"15","year":"2007","journal-title":"IEEE Trans. Audio. Speech Lang. Process."},{"key":"2025041808144826300_c35","volume-title":"Exploration Des Perspectives D'apprentissage Automatique Pour Les Signaux \u00c9lectroglottographiques","year":"2023"},{"key":"2025041808144826300_c11","doi-asserted-by":"publisher","first-page":"105604","DOI":"10.1016\/j.cmpb.2020.105604","article-title":"Classification of heart sound signals using a novel deep WaveNet model","volume":"196","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"2025041808144826300_c37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2012.04.009","article-title":"Analysis of longitudinal phase differences in vocal-fold vibration using synchronous high-speed videoendoscopy and electroglottography","volume":"26","year":"2012","journal-title":"J. Voice"},{"key":"2025041808144826300_c38","first-page":"90","article-title":"Mapping individual voice quality over the voice range: The measurement paradigm of the voice range profile","volume-title":"TRITA-EECS-AVL","year":"2018"},{"key":"2025041808144826300_c39","doi-asserted-by":"publisher","first-page":"337","DOI":"10.3109\/17549507.2014.894124","article-title":"Park play: A picture description task for assessing childhood motor speech disorders","volume":"16","year":"2014","journal-title":"Int. J. Speech Lang. Pathol."},{"key":"2025041808144826300_c40","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1177\/000348940811700603","article-title":"Comparison of high-speed digital imaging with stroboscopy for laryngeal imaging of glottal disorders","volume":"117","year":"2008","journal-title":"Ann. Otol. Rhinol. Laryngol."},{"key":"2025041808144826300_c41","first-page":"28","article-title":"Non-invasive evaluation of vibratory kinematics of phonation in children","year":"2020"},{"key":"2025041808144826300_c42","doi-asserted-by":"publisher","first-page":"2977","DOI":"10.1044\/2021_JSLHR-20-00717","article-title":"Quantitative and qualitative electroglottographic wave shape differences in children and adults using voice map-based analysis","volume":"64","year":"2021","journal-title":"J. Speech Lang. Hear. Res."},{"key":"2025041808144826300_c43","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1109\/TASLP.2019.2942140","article-title":"Adversarial approximate inference for speech to electroglottograph conversion","volume":"27","year":"2019","journal-title":"IEEE\/ACM Trans. Audio. Speech Lang. Process."},{"key":"2025041808144826300_c44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1159\/000263538","article-title":"Zur Quantitativen Auswertung Elektroglottographischer Kurven Bei Normalpersonen","volume":"24","year":"1972","journal-title":"Folia Phoniatr. Logop."},{"key":"2025041808144826300_c45","doi-asserted-by":"publisher","first-page":"1632","DOI":"10.1121\/1.1913513","article-title":"A new inverse-filtering technique for deriving the glottal air flow waveform during voicing","volume":"53","year":"1973","journal-title":"J. Acoust. Soc. Am."},{"key":"2025041808144826300_c46","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/S0892-1997(02)00069-3","article-title":"Correcting low-frequency phase distortion in electroglottograph waveforms","volume":"16","year":"2002","journal-title":"J. Voice"},{"key":"2025041808144826300_c47","doi-asserted-by":"publisher","first-page":"2773","DOI":"10.1121\/1.4896466","article-title":"Analysis of vibratory states in phonation using spectral features of the electroglottographic signal","volume":"136","year":"2014","journal-title":"J. Acoust. Soc. Am."},{"key":"2025041808144826300_c48","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1016\/j.jvoice.2016.11.003","article-title":"Investigation of the relationship between electroglottogram waveform, fundamental frequency, and sound pressure level using clustering","volume":"31","year":"2017","journal-title":"J. Voice"},{"key":"2025041808144826300_c49","first-page":"1","article-title":"Glottal instants extraction from speech signal using deep feature loss","year":"2022"},{"key":"2025041808144826300_c50","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1097\/MOO.0b013e3283581feb","article-title":"Kymographic imaging of laryngeal vibrations","volume":"20","year":"2012","journal-title":"Curr. Opin. Otolaryngol. Head Neck Surg."},{"key":"2025041808144826300_c51","doi-asserted-by":"publisher","first-page":"EL65","DOI":"10.1121\/1.5117174","article-title":"Normalized time-domain parameters for electroglottographic waveforms","volume":"146","year":"2019","journal-title":"J. Acoust. Soc. Am."},{"key":"2025041808144826300_c52","doi-asserted-by":"publisher","first-page":"479","DOI":"10.3390\/bioengineering11050479","article-title":"Pragmatic de-noising of electroglottographic signals","volume":"11","year":"2024","journal-title":"Bioengineering"},{"issue":"485","key":"2025041808144826300_c53","doi-asserted-by":"publisher","first-page":"485.e1","DOI":"10.1016\/j.jvoice.2018.09.006","article-title":"Effects of the lung volume on the electroglottographic waveform in trained female singers","volume":"34","year":"2020","journal-title":"J. Voice"},{"key":"2025041808144826300_c54","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.softx.2018.03.002","article-title":"FONADYN: A system for real-time analysis of the electroglottogram, over the voice range","volume":"7","year":"2018","journal-title":"SoftwareX"},{"key":"2025041808144826300_c55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0892-1997(05)80076-1","article-title":"Interpretation of the electroglottographic signal","volume":"4","year":"1990","journal-title":"J. Voice"},{"key":"2025041808144826300_c56","volume-title":"Principles of Voice Production","year":"1998"},{"key":"2025041808144826300_c36","year":"2016"},{"key":"2025041808144826300_c57","first-page":"6000","article-title":"Attention is all you need","year":"2017"},{"key":"2025041808144826300_c58","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/S0892-1997(98)80050-7","article-title":"Correspondence of electroglottographic closed quotient to vocal fold impact stress in excised canine larynges","volume":"12","year":"1998","journal-title":"J. Voice"}],"container-title":["The Journal of the Acoustical Society of America"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/157\/4\/3033\/20494636\/3033_1_10.0036514.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/157\/4\/3033\/20494636\/3033_1_10.0036514.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T08:15:06Z","timestamp":1744964106000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jasa\/article\/157\/4\/3033\/3344499\/A-WaveNet-based-model-for-predicting-the"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,1]]},"references-count":58,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4,1]]}},"URL":"https:\/\/doi.org\/10.1121\/10.0036514","relation":{},"ISSN":["1520-8524"],"issn-type":[{"value":"1520-8524","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,4]]},"published":{"date-parts":[[2025,4,1]]}}}