Summary
Objective
To identify and evaluate the best set of acoustic measures to discriminate among healthy,
rough, breathy, and strained voices.
Methods
This study used the vocal samples of the sustained /ε/ vowel from 251 patients with
the vocal complaints, among which 51, 80, 63, and 57 patients exhibited healthy, rough,
breathy, and strained voices, respectively. Twenty-two acoustic measures were extracted,
and feature selection was applied to reduce the number of combinations of acoustic
measures and obtain an optimal subset of measures according to the information gain
attribute ranking algorithm. To classify signals as a function of predominant voice
quality, a feedforward neural network was applied using a Levenberg-Marquardt supervised
learning algorithm.
Results
The best results were obtained from 11 combinations, with each combination presenting
six acoustic measures. Kappa indices ranged from 0.7527 to 0.7743, the overall hit
rates are 81.67%-83.27%, and the hit rates of healthy, rough, breathy, and strained
voices are 74.51%-84.31%, 78.75%-90.00%, 85.71%-98.41%, and 68.42%-82.46%, respectively.
Conclusions
We obtained the best results from 11 combinations, with each combination exhibiting
six acoustic measures for discriminating among healthy, rough, breathy, and strained
voices. These sets exhibited good Kappa performance and a good overall hit rate. The
hit rate varied between acceptable and good for healthy voices, acceptable and excellent
for rough voices, good and excellent for breathy voices, and poor and good for strained
voices.
Key Words
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Journal of VoiceAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- A basic protocol for functional assessment of voice pathology, especially for investigating the efficacy of (phonosurgical) treatments and evaluating new assessment techniques: Guideline elaborated by the Committee on Phoniatrics of the European Laryngolo.Eur Arch Oto-Rhino-Laryngol. 2001; 258: 77-82https://doi.org/10.1007/s004050000299
Souza BO, Gama ACC, Apoio visual do traçado espectrográfico: impacto na confiabilidade da análise perceptivo-auditiva da voz por avaliadores inexperientes, Distúrbios da Comunição; 2015 (3) 479-486.
- Recommended protocols for instrumental assessment of voice: American Speech-Language-Hearing Association Expert Panel to develop a protocol for instrumental assessment of vocal function.Am J Speech Lang Pathol. 2018; 27: 887-905https://doi.org/10.1044/2018_AJSLP-17-0009
- Categorizing normal and pathological voices: Automated and perceptual categorization.J Voice. 2010; 25: 700-708https://doi.org/10.1016/j.jvoice.2010.04.009
- Multi parametric voice assessment: Sri Ramachandra University Protocol.Indian J Otolaryngol Head Neck Surg. 2014; 66: 246-251https://doi.org/10.1007/s12070-011-0460-y
- Acoustic analysis of voice quality: a tabulation of algorithms 1902 -1990.in: Kent MJ Ball RD Voice Quality Measurement. 1st ed. Singular Publishing Group, 2000: 119-244
- Influence of size and etiology of glottal gap in glottic incompetence dysphonia.Laryngoscope. 1998; 108: 514-518https://doi.org/10.1097/00005537-199804000-00010
- Objective evaluation of the human voice: clinical aspects.Folia Phoniatr (Basel). 1989; 41: 89-144https://doi.org/10.1159/000265950
- Evidence-based clinical voice assessment: a systematic review.Am J Speech Lang Pathol. 2013; 22: 212-226https://doi.org/10.1044/1058-0360(2012/12-0014)
- Quantifying vocal fatigue recovery: dynamic vocal recovery trajectories after a vocal loading exercise.Ann Otol Rhinol Laryngol. 2009; 118: 449-460https://doi.org/10.1177/000348940911800608
- A meta-analysis: acoustic measurement of roughness and breathiness.J Speech Lang Hear Res. 2018; 61: 298-323https://doi.org/10.1044/2017_JSLHR-S-16-0188
- Differential diagnosis of hoarseness.Folia Phoniatr (Basel). 1969; 21: 9-19https://doi.org/10.1159/000263230
- Clinical examination of voice by Minoru Hirano.J Acoust Soc Am. 1986; 80: 1273https://doi.org/10.1121/1.393788
- Consensus auditory-perceptual evaluation of voice: development of a standardized clinical protocol.Am J Speech Lang Pathol. 2009; 18: 124-132https://doi.org/10.1044/1058-0360(2008/08-0017)
- Auditory-perceptual evaluation of normal and dysphonic voices using the voice deviation scale.J Voice. 2017; 31: 67-71https://doi.org/10.1016/j.jvoice.2016.01.004
- A perceptual protocol for the analysis of vocal profiles.Edinb Univ Dep. Linguist Work Prog. 1981; 14: 139-155
- Auditory-perceptual evaluation of disordered voice quality.Folia Phoniatr (Basel). 2009; 61: 49-56https://doi.org/10.1159/000200768
- Perceptual evaluation of voice quality and its correlation with acoustic Measurements.J Voice. 2004; 18: 299-304https://doi.org/10.1016/j.jvoice.2003.12.004
- Validity of jitter measures innon-quasi-periodic voices. Part I: perceptual and computer performances in cycle pattern recognition.Logoped Phoniatr Vocol. 2011; 36: 70-77https://doi.org/10.3109/14015439.2011.578078
- Speech tasks and interrater reliability in perceptual voice evaluation.J Voice. 2014; 28: 725-732https://doi.org/10.1016/j.jvoice.2014.01.018
- Auditory-perceptual evaluation of rough and breathy voices: correspondence between analogical visual and numericalscale.Codas. 2016; 28: 163-167https://doi.org/10.1590/2317-1782/20162015098
- Identification of pathological voices using glottal noise measures.J Speech Lang Hear Res. 2000; 43: 469-485https://doi.org/10.1044/jslhr.4302.469
- The relationship between cepstral peak prominence and selected parameters of dysphonia.J Voice. 2002; 16: 20-27https://doi.org/10.1016/S0892-1997(02)00067-X
- Severity of voice disorders: integration of perceptual and acoustic data in dysphonic patients.Codas. 2014; 26: 382-388https://doi.org/10.1590/2317-1782/20142013033
- Objective indices of perceived vocal strain.J Voice. 2019; 33: 838-845https://doi.org/10.1016/j.jvoice.2018.06.005
- Cepstral measures in the assessment of severity of voice disorders.Codas. 2019; 31: 1-8https://doi.org/10.1590/2317-1782/20182018175
- Performance of phonatory deviation diagrams in synthesized voice analysis.Folia Phoniatr (Basel). 2017; 69: 246-260https://doi.org/10.1159/000487941
- Acoustic measurement of overall voice quality: a meta-analysis.J Acoust Soc Am. 2009; 126: 2619-2634https://doi.org/10.1121/1.3224706
- Routine acoustic voice analysis: time to think again?.Curr Opin Otolaryngol Head Neck Surg. 2011; 19: 165-170https://doi.org/10.1097/MOO.0b013e32834575fe
- Use of cepstral analyses fordifferentiating normal from dysphonic voices: a comparative study of connected speech versus sustained vowel in European Portuguese female speakers.J Voice. 2014; 28: 282-286https://doi.org/10.1016/j.jvoice.2013.10.001
- The acoustic breathiness index (ABI): a multivariate acoustic model for breathiness.J Voice. 2017; 31 (511.e11-511.e27)https://doi.org/10.1016/j.jvoice.2016.11.017
- Functional dysphonia: strategies to improve patient outcomes.Patient Relat Outcome Meas. 2015; 6: 243-253https://doi.org/10.2147/prom.s68631
- Exploring the relationship between spectral and cepstral measures of voice and the voice handicap index (VHI).J Voice. 2014; 28: 430-439https://doi.org/10.1016/j.jvoice.2013.12.008
- Spectral- and cepstral-based acousticfeatures of dysphonic, strained voice quality.Ann Otol Rhinol Laryngol. 2012; 121: 539-548https://doi.org/10.1177/000348941212100808
- The exploration of an objective model for roughness with several acoustic markers.J Voice. 2018; 32: 149-161https://doi.org/10.1016/j.jvoice.2017.04.017
- Transfer function of Brazilian Portuguese oral vowels: a comparative acoustic analysis.Braz J Otorhinolaryngol. 2009; 75: 680-684
- A coefficient of agreement for nominal scales.Educ Psychol Meas. 1960; 20: 37-46https://doi.org/10.1177/001316446002000104
- C4.5: Programs for Machine Learning, Ebrary Online.Elsevier Science, 2014
- Training feedforward networks with the Marquardt algorithm.IEEE Trans Neural Netw. 1994; 5: 989-993https://doi.org/10.1109/72.329697
- A review of assessing the accuracy of classifications of remotely sensed data.Remote Sens Environ. 1991; 37: 35-46https://doi.org/10.1016/0034-4257(91)90048-B
- The measurement of observer agreement for categorical data.Biometrics. 1977; 33: 159https://doi.org/10.2307/2529310
Hosmer DW, Lemeshow S, Sturdivant RX, Applied logistic regression, Wiley Series in Probability and Statistics, Wiley 2013.
- Effectiveness of recurrence quantification measures in discriminating subjects with and without voice disorders.J Voice. 2020; 34: 208-220https://doi.org/10.1016/j.jvoice.2018.09.004
- An evaluation of residue features as correlates of voice disorders.J Commun Disord. 1987; 20: 105-117https://doi.org/10.1016/0021-9924(87)90002-5
- Accuracy of traditional and formant acoustic measurements in the evaluation of vocal quality.Codas. 2018; 30: 1-10https://doi.org/10.1590/2317-1782/20182017282
Article info
Publication history
Published online: August 23, 2022
Accepted:
July 5,
2022
Publication stage
In Press Corrected ProofIdentification
Copyright
© 2022 The Voice Foundation. Published by Elsevier Inc. All rights reserved.
