{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T02:22:48Z","timestamp":1791080568170,"version":"4.1.0"},"reference-count":77,"publisher":"Elsevier BV","issue":"3","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"am","delay-in-days":365,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJSP2136"],"award-info":[{"award-number":["JPMJSP2136"]}],"id":[{"id":"10.13039\/501100002241","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":[[2025,5]]},"DOI":"10.1016\/j.jvoice.2022.10.020","type":"journal-article","created":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T07:42:25Z","timestamp":1669362145000},"page":"846.e1-846.e23","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":12,"title":["Automatic GRBAS Scoring of Pathological Voices using Deep Learning and a Small Set of Labeled Voice Data"],"prefix":"10.1016","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1001-4564","authenticated-orcid":false,"given":"Shunsuke","family":"Hidaka","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yogaku","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3009-2244","authenticated-orcid":false,"given":"Moe","family":"Nakanishi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9254-5910","authenticated-orcid":false,"given":"Kohei","family":"Wakamiya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3198-639X","authenticated-orcid":false,"given":"Takashi","family":"Nakagawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tokihiko","family":"Kaburagi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2022.10.020_bib0001","first-page":"248","article-title":"Diagnosis of voice disorders","volume":"54","author":"Omori","year":"2011","journal-title":"Japan Med Assoc J"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0002","doi-asserted-by":"crossref","first-page":"2004","DOI":"10.1002\/lary.21895","article-title":"Quality of life indicators according to voice disorders and voice-related conditions","volume":"121","author":"Merrill","year":"2011","journal-title":"Laryngoscope"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0003","series-title":"Acoustic Measurement of Overall Voice Quality in Sustained Vowels and Continuous Speech","author":"Maryn","year":"2010"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0004","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1044\/jshr.3601.21","article-title":"Perceptual evaluation of voice quality: review, tutorial, and a framework for future research","volume":"36","author":"Kreiman","year":"1993","journal-title":"J Speech Hear Res"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0005","series-title":"Clinical Examination of Voice: Disorders of Human Communication","first-page":"81","article-title":"Psycho-acoustic evaluation of voice","author":"Hirano","year":"1981"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0006","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1017\/S0022215109005398","article-title":"Measuring voice outcomes: state of the science review","volume":"123","author":"Carding","year":"2009","journal-title":"J Laryngol Otol"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0007","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/S0892-1997(97)80026-4","article-title":"Test-retest study of the GRBAS scale: influence of experience and professional background on perceptual rating of voice quality","volume":"11","author":"De Bodt","year":"1997","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0008","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/j.jvoice.2005.08.007","article-title":"The effect of perceptual training on inexperienced listeners\u2019 judgments of dysphonic voice","volume":"20","author":"Eadie","year":"2006","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0009","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1111\/j.1365-2273.2004.00846.x","article-title":"The reliability and sensitivity to change of acoustic measures of voice quality","volume":"29","author":"Carding","year":"2004","journal-title":"Clin Otolaryngol Allied Sci"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0010","doi-asserted-by":"crossref","first-page":"2551","DOI":"10.1121\/1.2005907","article-title":"Comparison of nonlinear dynamic methods and perturbation methods for voice analysis","volume":"118","author":"Zhang","year":"2005","journal-title":"J Acoust Soc Am"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0011","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1080\/02699200400008353","article-title":"Toward the development of an objective index of dysphonia severity: a four-factor acoustic model","volume":"20","author":"Awan","year":"2006","journal-title":"Clin Linguist Phon"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0012","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1044\/jshr.3902.311","article-title":"Acoustic correlates of breathy vocal quality: dysphonic voices and continuous speech","volume":"39","author":"Hillenbrand","year":"1996","journal-title":"J Speech Lang Hear Res"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0013","doi-asserted-by":"crossref","DOI":"10.1155\/2015\/259239","article-title":"Modulation Spectra Morphological Parameters: a New Method to Assess Voice Pathologies according to the GRBAS Scale","author":"Moro-Vel\u00e1zquez","year":"2015","journal-title":"Biomed Res Int"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0014","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.jvoice.2005.01.001","article-title":"Chaos in voice, from modeling to measurement","volume":"20","author":"Jiang","year":"2006","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0015","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.jvoice.2020.02.009","article-title":"Classification of voice disorders using a one-dimensional convolutional neural network","volume":"36","author":"Fujimura","year":"2022","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0016","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1016\/j.jvoice.2008.12.014","article-title":"Toward improved ecological validity in the acoustic measurement of overall voice quality: combining continuous speech and sustained vowels","volume":"24","author":"Maryn","year":"2010","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0017","doi-asserted-by":"crossref","first-page":"511e11","DOI":"10.1016\/j.jvoice.2016.11.017","article-title":"The Acoustic Breathiness Index (ABI): a multivariate acoustic model for breathiness","volume":"31","author":"Barsties v. Latoszek","year":"2017","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0018","first-page":"2478","article-title":"Automatic assessment of voice quality according to the GRBAS scale","author":"S\u00e1enz-Lech\u00f3n","year":"2006","journal-title":"EMBC"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0019","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/s11265-015-1016-2","article-title":"Automatic assessment of pathological voice quality using multidimensional acoustic analysis based on the GRBAS scale","volume":"82","author":"Wang","year":"2016","journal-title":"J Signal Process Syst"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0020","doi-asserted-by":"crossref","first-page":"1892","DOI":"10.1109\/TASLP.2022.3178239","article-title":"Emulating perceptual evaluation of voice using scattering transform based features","volume":"30","author":"Miramont","year":"2022","journal-title":"IEEE\/ACM Trans Audio, Speech Lang Process"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0021","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.engappai.2019.03.027","article-title":"Emulating the perceptual capabilities of a human evaluator to map the GRB scale for the assessment of voice disorders","volume":"82","author":"G\u00f3mez-Garc\u00eda","year":"2019","journal-title":"Eng Appl Artif Intell"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0022","first-page":"111","article-title":"Automatic GRBAS assessment using complexity measures and a multiclass GMM-based detector","author":"Arias-Londo\u00f1o","year":"2011","journal-title":"MAVEBA"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0023","doi-asserted-by":"crossref","first-page":"2656","DOI":"10.21437\/Interspeech.2016-986","article-title":"Deep neural networks for voice quality assessment based on the GRBAS scale","author":"Xie","year":"2016","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0024","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1109\/JSTSP.2019.2956410","article-title":"Multimodal and multi-output deep learning architectures for the automatic assessment of voice quality using the GRB scale","volume":"14","author":"Arias-Londo\u00f1o","year":"2020","journal-title":"IEEE J Sel Top Signal Process"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0025","first-page":"3880","article-title":"automatic estimation of pathological voice quality based on recurrent neural network using amplitude and phase spectrogram","author":"Hidaka","year":"2020","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0026","article-title":"Objective assessment of pathological voice using artificial intelligence based on the GRBAS scale","author":"Kojima","year":"2021","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0027","article-title":"Deep neural network for automatic assessment of dysphonia","author":"Garc\u00eda","year":"2022","journal-title":"arXiv [eessAS]"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0028","first-page":"1653","article-title":"The importance of phase on voice quality assessment","author":"Koutsogiannaki","year":"2014","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0029","first-page":"4612","article-title":"Phase-based information for voice pathology detection","author":"Drugman","year":"2011","journal-title":"ICASSP"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0030","first-page":"6477","article-title":"Experimental investigation on STFT phase representations for deep learning-based Dysarthric Speech Detection","author":"Janbakhshi","year":"2022","journal-title":"ICASSP"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0031","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"Ko","year":"2015","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0032","first-page":"2613","article-title":"SpecAugment: a simple data augmentation method for automatic speech recognition","author":"Park","year":"2019","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0033","doi-asserted-by":"crossref","first-page":"195","DOI":"10.3758\/s13428-018-01193-y","article-title":"PsychoPy2: experiments in behavior made easy","volume":"51","author":"Peirce","year":"2019","journal-title":"Behav Res Methods"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0034","doi-asserted-by":"crossref","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","author":"Kempster","year":"2009","journal-title":"Am J Speech Lang Pathol"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0035","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1044\/1092-4388(2010\/09-0205)","article-title":"The effect of listener experience and anchors on judgments of dysphonia","volume":"54","author":"Eadie","year":"2011","journal-title":"J Speech Lang Hear Res"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0036","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/j.jvoice.2007.10.006","article-title":"The effect of anchor modality on the reliability of vocal severity ratings","volume":"23","author":"Awan","year":"2009","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0037","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A coefficient of agreement for nominal scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educ Psychol Meas"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0038","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1037\/h0026256","article-title":"Weighted kappa: nominal scale agreement provision for scaled disagreement or partial credit","volume":"70","author":"Cohen","year":"1968","journal-title":"Psychol Bull"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0039","article-title":"Handbook of inter-rater reliability, 4th edition: the definitive guide to measuring the extent of agreement among Raters","author":"Gwet","year":"2014","journal-title":"Gaithersburg: Advanced Analytics, LLC"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0040","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1037\/0033-2909.88.2.322","article-title":"Integration and generalization of kappas for multiple raters","volume":"88","author":"Conger","year":"1980","journal-title":"Psychol Bull"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0041","first-page":"8024","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0042","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1016\/j.acha.2015.10.001","article-title":"The pole behavior of the phase derivative of the short-time Fourier transform","volume":"40","author":"Balazs","year":"2016","journal-title":"Appl Comput Harmon Anal"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0043","first-page":"424","article-title":"A modulation property of time-frequency derivatives of filtered phase and its application to aperiodicity and fo estimation","author":"Kawahara","year":"2017","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0044","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1109\/78.382394","article-title":"Improving the readability of time-frequency and time-scale representations by the reassignment method","volume":"43","author":"Auger","year":"1995","journal-title":"IEEE Trans Signal Process"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0045","first-page":"448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"ICML"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0046","series-title":"The HTK Book. 3.4","author":"Young","year":"2006"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0047","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0048","first-page":"10096","article-title":"Le Q. EfficientNetV2: smaller models and faster training","author":"Tan","year":"2021","journal-title":"ICML"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0049","article-title":"PyTorch image models","author":"Wightman","year":"2019","journal-title":"GitHub repository"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0050","doi-asserted-by":"crossref","first-page":"2825","DOI":"10.1109\/TIP.2017.2689998","article-title":"Deep label distribution learning with label ambiguity","volume":"26","author":"Gao","year":"2017","journal-title":"IEEE Trans Image Process"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0051","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann Math Stat"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0052","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv [csLG]"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0053","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1177\/001316447003000105","article-title":"Estimating the reliability, systematic error and random error of interval data","volume":"30","author":"Krippendorff","year":"1970","journal-title":"Educ Psychol Meas"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0054","first-page":"696","article-title":"Investigation of data augmentation techniques for disordered speech recognition","author":"Geng","year":"2020","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0055","first-page":"361","article-title":"Local group delay based vibrato and tremolo suppression for onset detection","author":"B\u00f6ck","year":"2013","journal-title":"ISMIR"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0056","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1044\/jshr.3705.985","article-title":"Consistency and reliability of voice quality ratings for different types of speech fragments","volume":"37","author":"de Krom","year":"1994","journal-title":"J Speech Hear Res"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0057","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1159\/000021485","article-title":"Comparison of different voice samples for perceptual analysis","volume":"51","author":"Revis","year":"1999","journal-title":"Folia Phoniatr Logop"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0058","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.specom.2016.09.001","article-title":"D4C, a band-aperiodicity estimator for high-quality speech synthesis","volume":"84","author":"Morise","year":"2016","journal-title":"Speech Commun"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0059","doi-asserted-by":"crossref","first-page":"1877","DOI":"10.1587\/transinf.2015EDP7457","article-title":"WORLD: a vocoder-based high-quality speech synthesis system for real-time applications","volume":"E99.D","author":"Morise","year":"2016","journal-title":"IEICE Trans Inf Syst"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0060","first-page":"1121","article-title":"Instantaneous-frequency distribution vs. time: an interpretation of the phase structure of speech","author":"Friedman","year":"1985","journal-title":"ICASSP"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0061","first-page":"81","article-title":"Formant detection through instantaneous-frequency estimation using recursive least square algorithm","author":"Ghaemmaghami","year":"1996","journal-title":"ISSPA"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0062","first-page":"219","article-title":"Differentiated perceptual evaluation of pathological voice quality: reliability and correlations with acoustic measurements","volume":"117","author":"Dejonckere","year":"1996","journal-title":"Rev Laryngol Otol Rhinol"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0063","series-title":"Surgery of Larynx and Trachea","first-page":"11","article-title":"Assessment of Voice and Respiratory Function","author":"Dejonckere","year":"2010"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0064","first-page":"3149","article-title":"LightGBM: a highly efficient gradient boosting decision tree","author":"Ke","year":"2017","journal-title":"NIPS"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0065","doi-asserted-by":"crossref","first-page":"15747","DOI":"10.1007\/s00521-018-3464-7","article-title":"Towards robust voice pathology detection","volume":"32","author":"Harar","year":"2020","journal-title":"Neural Comput Appl"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0066","first-page":"1292","article-title":"Detection of Parkinson's disease using LightGBM Classifier","author":"Kumar","year":"2022","journal-title":"ICCMC"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0067","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1016\/j.jvoice.2017.12.018","article-title":"Perceptual and quantitative assessment of dysphonia across vowel categories","volume":"33","author":"Anand","year":"2019","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0068","article-title":"Perceptual voice qualities database (PVQD): database characteristics","author":"Walden","year":"2020","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0069","first-page":"406","article-title":"Speaker augmentation and bandwidth extension for deep speaker embedding","author":"Yamamoto","year":"2019","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0070","first-page":"6211","article-title":"Speaker characterization using TDNN-LSTM based speaker embedding","author":"Chen","year":"2019","journal-title":"ICASSP"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0071","unstructured":"P\u00fctzer M, Barry WJ. Saarbruecken Voice Database. Available at: http:\/\/www.stimmdatenbank.coli.uni-saarland.de\/. Accessed July 1, 2022."},{"key":"10.1016\/j.jvoice.2022.10.020_bib0072","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1016\/j.jvoice.2018.06.005","article-title":"Objective indices of perceived vocal strain","volume":"33","author":"Anand","year":"2019","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0073","first-page":"700","article-title":"Glottal-to-noise excitation ratio - a new measure for describing pathological voices","volume":"83","author":"Michaelis","year":"1997","journal-title":"Acustica"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0074","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1097\/00004356-198403000-00015","article-title":"Recognition of hoarseness by means of LTAS","volume":"7","author":"Dejonckere","year":"1983","journal-title":"Int J Rehabil Res"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0075","first-page":"988","article-title":"Harmonic emergence in formant zone of a sustained [a] as a parameter for evaluating hoarseness","volume":"41","author":"Dejonckere","year":"1987","journal-title":"Acta Otorhinolaryngol Belg"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0076","series-title":"Psychoacoustics: Facts and Models","first-page":"239","article-title":"Sharpness and sensory pleasantness","author":"Fastl","year":"2007"},{"key":"10.1016\/j.jvoice.2022.10.020_bib0077","first-page":"2623","article-title":"Optuna: a next-generation hyperparameter optimization framework","author":"Akiba","year":"2019","journal-title":"KDD"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199722003472?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199722003472?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T19:49:32Z","timestamp":1775072972000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199722003472"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":77,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["S0892199722003472"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2022.10.020","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2025,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Automatic GRBAS Scoring of Pathological Voices using Deep Learning and a Small Set of Labeled Voice Data","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2022.10.020","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2022 The Voice Foundation. Published by Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}