Voice Pathology Detection and Classification Using Auto-Correlation and Entropy Features in Different Frequency Regions
Open accessThe DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
Automatic voice pathology detection and classification systems effectively contribute to the assessment of voice disorders, enabling the early detection of voice pathologies and the diagnosis of the type of pathology from which patients suffer. This paper concentrates on developing an accurate and robust feature extraction for detecting and classifying voice pathologies by investigating different frequency bands using autocorrelation and entropy. We extracted maximum peak values and their corresponding lag values from each frame of a voiced signal by using autocorrelation as features to detect and classify pathological samples. We also extracted the entropy for each frame of the voice signal after we normalized its values to be used as the features. These features were investigated in distinct frequency bands to assess the contribution of each band to the detection and classification processes. Various samples of the sustained vowel /a/ for both normal and pathological voices were extracted from three different databases in English, German, and Arabic. A support vector machine was used as a classifier. We also performed u-tests to investigate if there is a significant difference between the means of the normal and pathological samples. The best achieved accuracies in both detection and classification varied depending on the used band, method, and database. The most contributive bands in both detection and classification were between 1000 and 8000 Hz. The highest obtained accuracies in the case of detection were 99.69%, 92.79%, and 99.79% for Massachusetts eye and ear infirmary (MEEI), Saarbrücken voice database (SVD), and Arabic voice pathology database (AVPD), respectively. However, the highest achieved accuracies for classification were 99.54%, 99.53%, and 96.02% for MEEI, SVD, and AVPD, correspondingly, using the combined feature.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source doesn’t support the claim as written.
In the citing paper
“Gaussian mixture models: Achieved an accuracy, sensitivity, and specificity percentages of 100% in study 35 to identify pathological voices from health voices using the Massachusetts Eye and Ear Infirmary (MEEI) Database”
From The role of AI in the diagnosis of speech and language disorders: A systematic mapping study (2025) · cites this paper as [26]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The partial automation of the third phase has been achieved in certain disorders such as voice disorders, where AI machine learning algorithms automatically classify certain vocal pathologies into subtypes such as vocal fold cysts, unilateral vocal fold paralysis, and vocal fold polyps. 26”
From The role of AI in the diagnosis of speech and language disorders: A systematic mapping study (2025) · cites this paper as [26]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, voice disorders require automated diagnostic methods, as the current diagnostic procedures lack standard methods and equipment. 26”
From The role of AI in the diagnosis of speech and language disorders: A systematic mapping study (2025) · cites this paper as [26]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Support vector machine: Achieved an accuracy, sensitivity, and specificity percentages of 99.96% in 26 study to identify pathological voices affected by vocal fold cysts, unilateral vocal fold paralysis, and vocal fold polyps from healthy voices using the MEEI Database.”
From The role of AI in the diagnosis of speech and language disorders: A systematic mapping study (2025) · cites this paper as [26]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Fundamentals of speech recognition
Rabiner, L. R., & Juang, B.-H. F. (1993) · Cited by 7,680
Statistical Inference for Probabilistic Functions of Finite State Markov Chains
Baum, L. E., & Petrie, T. (1966) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177699147 · Cited by 2,775 · cited 1×
“Various machine-learning algorithms, such as Gaussian mixture model [13], [14], hidden Markov model [15], support vector machine (SVM) [16], artificial neural network [17], and so”
MethodPrevalence of Voice Disorders in Teachers and the General Population
Roy, N., Merrill, R. M., Thibeault, S., Parsa, R. A., Gray, S. D., & Smith, E. M. (2004) · Journal of Speech, Language, and Hearing Research · doi:10.1044/1092-4388(2004/023 · Cited by 925
Atal, B. S. (1974) · The Journal of the Acoustical Society of America · doi:10.1121/1.1914702 · Cited by 915 · cited 1×
“Whilst the parameters of long-term signal analyses can be taken from the acoustic analysis [6] of a speech signal or Big data [7], the parameters of short-term signal analyses can be computed by using linear predictive coefficients [8], wear-”
BackgroundSupport Vector Machines for Pattern Classification
(2005) · Advances in Pattern Recognition · doi:10.1007/1-84628-219-5 · Cited by 852
Smart Clothing: Connecting Human with Clouds and Big Data for Sustainable Health Monitoring
Chen, M., Ma, Y., Song, J., Lai, C.-F., & Hu, B. (2016) · Mobile Networks and Applications · doi:10.1007/s11036-016-0745-1 · Cited by 443 · cited 1×
“Whilst the parameters of long-term signal analyses can be taken from the acoustic analysis [6] of a speech signal or Big data [7], the parameters of short-term signal analyses can be computed by using linear predictive coefficients [8], wear-”
BackgroundWearable 2.0: Enabling Human-Cloud Integration in Next Generation Healthcare Systems
Chen, M., Ma, Y., Li, Y., Wu, D., Zhang, Y., & Youn, C.-H. (2017) · IEEE Communications Magazine · doi:10.1109/mcom.2017.1600410cm · Cited by 373 · cited 1×
“0 [9], linear predictive cepstral coefficients [10], Melfrequency cepstral coefficients [11], [12], and so on.”
BackgroundKent, R. D., & Kim, Y. (2008) · The Handbook of Clinical Linguistics · doi:10.1002/9781444301007.ch22 · Cited by 336 · cited 1×
“However, an accurate detailed analysis must realize that the infralaryngeal structures do influence the vocal tract and that the articulatory configuration in the vocal tract interacts with the articulation in the vocal folds [38].”
BackgroundGodino-Llorente, J. I., Gomez-Vilda, P., & Blanco-Velasco, M. (2006) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2006.871883 · Cited by 322 · cited 3×
“In reality, there are diverse numbers of long-term acoustic features such as pitch, shimmer, jitter, amplitude perturbation quotient, pitch perturbation quotient, harmonic-to-noise ratio, normalized noise energy, voice turbulence index, soft phonation index, frequency amplitude tremor, and glottal-to-noise excitation…”
BackgroundMethodThe Handbook of Clinical Linguistics
(2008) · Wiley eBooks · doi:10.1002/9781444301007 · Cited by 193
Lieberman, P. (1961) · The Journal of the Acoustical Society of America · doi:10.1121/1.1908736 · Cited by 189 · cited 1×
“that pathological voices tend to show unusually large cycleto-cycle fluctuations in the fundamental period [30].”
BackgroundMethodological issues in the development of automatic systems for voice pathology detection
Sáenz-Lechón, N., Godino-Llorente, J. I., Osma-Ruiz, V., & Gómez-Vilda, P. (2006) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2006.06.003 · Cited by 175 · cited 2×
“compared their proposed parameters based on wavelet transform with some of the MDVP parameters to discriminate between pathological and normal samples [24].”
MethodChen, M., Zhou, P., & Fortino, G. (2017) · IEEE Access · doi:10.1109/access.2016.2641480 · Cited by 150 · cited 1×
“These parameters are widely used in other systems [18].”
BackgroundBoyanov, B., & Hadjitodorov, S. (1997) · IEEE Engineering in Medicine and Biology Magazine · doi:10.1109/51.603651 · Cited by 137 · cited 1×
“Whilst the parameters of long-term signal analyses can be taken from the acoustic analysis [6] of a speech signal or Big data [7], the parameters of short-term signal analyses can be computed by using linear predictive coefficients [8], wear-”
BackgroundVoice Pathology Detection and Discrimination Based on Modulation Spectral Features
Markaki, M., & Stylianou, Y. (2011) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2010.2104141 · Cited by 131 · cited 1×
“[35] used the MEEI database and the attained accuracy for the classification was 94.”
MethodAdaptive estimation of residue signal for voice pathology diagnosis
de Oliveira Rosa, M., Pereira, J. C., & Grellet, M. (2000) · IEEE Transactions on Biomedical Engineering · doi:10.1109/10.817624 · Cited by 129 · cited 1×
“[19], where jitter obtained 54.”
Cloud-Assisted Speech and Face Recognition Framework for Health Monitoring
Hossain, M. S., & Muhammad, G. (2015) · Mobile Networks and Applications · doi:10.1007/s11036-015-0586-3 · Cited by 124 · cited 1×
“0 [9], linear predictive cepstral coefficients [10], Melfrequency cepstral coefficients [11], [12], and so on.”
BackgroundSelf-citationPatient State Recognition System for Healthcare Using Speech and Facial Expressions
Hossain, M. S. (2016) · Journal of Medical Systems · doi:10.1007/s10916-016-0627-x · Cited by 112 · cited 1×
“Various machine-learning algorithms, such as Gaussian mixture model [13], [14], hidden Markov model [15], support vector machine (SVM) [16], artificial neural network [17], and so”
MethodThe short-time modified coherence representation and noisy speech recognition
Mansour, D., & Juang, B.-H. (1989) · IEEE Transactions on Acoustics Speech and Signal Processing · doi:10.1109/assp.1989.28053 · Cited by 109 · cited 1×
“It is preferable to use a short segment of the voice signal instead of the whole signal, because the noise tends to be cancelled out in the autocorrelation process in this short segment [31].”
MethodMartínez, D., Lleida, E., Ortega, A., Miguel, A., & Villalba, J. (2012) · Communications in computer and information science · doi:10.1007/978-3-642-35292-8_11 · Cited by 94 · cited 1×
“[34] used the SVD and same classifier that we used and attained an accuracy of 81%.”
MethodPathological voice detection and binary classification using MPEG-7 audio features
Muhammad, G., & Melhem, M. (2014) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2014.02.001 · Cited by 92 · cited 2×
“10%, while Muhammad andMelhem [26] used theMPEG feature to detect and classify the voice pathology by using”
MethodSelf-citationPathological voice quality assessment using artificial neural networks
Ritchings, R. T., McGillion, M., & Moore, C. J. (2002) · Medical Engineering & Physics · doi:10.1016/s1350-4533(02)00064-4 · Cited by 90
Laryngeal Vibrations: Measurements of the Glottic Wave: Part III. The Pathologic Larynx
von Leden, H., MOORE, P., & Timcke, R. (1960) · Archives of Otolaryngology - Head and Neck Surgery · doi:10.1001/archotol.1960.03770010020003 · Cited by 86 · cited 1×
“For instance, Von Leden, Moore, and Timke observed that pathological samples have a strong tendency for frequent and rapid changes in regularity [29].”
BackgroundArjmandi, M. K., Pooyan, M., Mikaeili, M., Vali, M., & Moqarehzadeh, A. (2010) · Journal of Voice · doi:10.1016/j.jvoice.2010.08.003 · Cited by 82 · cited 2×
“55% for detection and classification, respectively in [21], where Arjmandi et al.”
BackgroundMethodWoldert-Jokisz, B. (2007) · Cited by 74
Multidirectional Regression (MDR)-Based Features for Automatic Voice Disorder Detection
Muhammad, G., Mesallam, T. A., Malki, K. H., Farahat, M., Mahmood, A., & Alsulaiman, M. (2012) · Journal of Voice · doi:10.1016/j.jvoice.2012.05.002 · Cited by 66 · cited 1×
“, MPEG-7 audio descriptors and multidirectional approaches) have been used for determining voice pathologies, with high accuracy of detection [26], [27].”
MethodSelf-citationComparison of results in two acoustic analysis programs: Praat and MDVP
Oğuz, H., KILIÇ, M. A., & Şafak, M. A. (2011) · TURKISH JOURNAL OF MEDICAL SCIENCES · doi:10.3906/sag-0909-290 · Cited by 66 · cited 1×
“The results showed no significant difference between the two computer software approaches [25].”
ResultAutomatic voice pathology detection and classification using vocal tract area irregularity
Muhammad, G., Altuwaijri, G. A., Alsulaiman, M., Ali, Z., Mesallam, T. A., Farahat, M., Malki, K. H., & Al-nasheri, A. (2016) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2016.01.004 · Cited by 58 · cited 1×
“Voice disorders also affect the shape of the vocal tract (supra-glottal) and produce irregularities in spectral properties [1].”
BackgroundSelf-citationA Speaker Identification System Using MFCC Features with VQ Technique
Zulfiqar, A., Aslam, M., & Martinez Enriquez, A. M. (2009) · Intelligent Information Technology Application · doi:10.1109/iita.2009.420 · Cited by 50 · cited 2×
“In reality, there are diverse numbers of long-term acoustic features such as pitch, shimmer, jitter, amplitude perturbation quotient, pitch perturbation quotient, harmonic-to-noise ratio, normalized noise energy, voice turbulence index, soft phonation index, frequency amplitude tremor, and glottal-to-noise excitation…”
BackgroundVocal Folds Disorder Detection using Pattern Recognition Methods
Wang, J., & Jo, C. (2007) · 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2007.4353023 · Cited by 49 · cited 1×
“[22], Mel-frequency cepstral coefficients and six acoustic parameters (jitter, shimmer, harmonic-to-noise ratio, soft phonation index, amplitude perturbation quotient, and relative average perturbation) were extracted, with the results compared with those of the neural network-based voice pathology detection system [2…”
An Investigation of Vocal Tract Characteristics for Acoustic Discrimination of Pathological Voices
Lee, J.-W., Kang, H.-G., Choi, J.-Y., & Son, Y.-I. (2013) · BioMed Research International · doi:10.1155/2013/758731 · Cited by 47 · cited 1×
“of the vocal folds, essentially during phonation [39].”
BackgroundAutomatic voice disorder classification using vowel formants
Muhammad, G., Alsulaiman, M., Mahmood, A., & Ali, Z. (2011) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2011.6012187 · Cited by 34 · cited 1×
“detection [40].”
Self-citationVoice pathology detection using auto-correlation of different filters bank
Al-nasheri, A., Ali, Z., Muhammad, G., & Alsulaiman, M. (2014) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa.2014.7073178 · Cited by 24 · cited 1×
“frequency region for voice pathology detection [28].”
Self-citationFraile, R., Godino-Llorente, J. I., Sáenz-Lechón, N., Osma-Ruiz, V., & Gutiérrez-Arriola, J. M. (2012) · Journal of Voice · doi:10.1016/j.jvoice.2012.07.004 · Cited by 22 · cited 2×
“[36], who state that ‘‘the power of dysphonic voices’ signal is significantly less stable in the frequency region between 2000 and 6400 Hz than the other frequency regions.”
BackgroundVoice disorders among Saudi teachers in Riyadh City
Malki, K. H. (2010) · Saudi Journal of Otorhinolaryngology Head and Neck Surgery · doi:10.4103/1319-8491.274630 · Cited by 19 · cited 1×
“Further, in the Riyadh area of Saudi Arabia, around 33% of male and female teachers experience voice disorders at some point in their lives [5].”
BackgroundSelf-citationClassification of pathological voice including severely noisy cases
Jo, C., Wang, S.-G., Yang, B., Kim, H.-S., & Li, T. (2004) · Interspeech (USB) · doi:10.21437/interspeech.2004-85 · Cited by 14 · cited 1×
“[22], Mel-frequency cepstral coefficients and six acoustic parameters (jitter, shimmer, harmonic-to-noise ratio, soft phonation index, amplitude perturbation quotient, and relative average perturbation) were extracted, with the results compared with those of the neural network-based voice pathology detection system [2…”
CHARACTERIZATION OF THE PATHOLOGICAL VOICES (DYSPHONIA) IN THE FREQUENCY SPACE
Pouchoulin, G., Fredouille, C., Bonastre, J.-F., Ghio, A., & Révis, J. (2007) · HAL · Cited by 6
An investigation of MDVP parameters for voice pathology detection on three different databases
Al-nasheri, A., Ali, Z., Muhammad, G., & Alsulaiman, M. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-611 · Cited by 5
Self-citation
Research works printed but not linked: 4
- 1994, Disordered Voice Database Version 1 03 (CD-ROM) MEEI Voice and Speech Lab
- 2015, Research Chair of Voicing and Swallowing Disorders
- 2014, National Institute on Deafness and Other Communication Disorders Voice Speech and Language Quick Statistics
- 2012, J Multi-Dimensional Voice Program (MDVP) [Computer Program]
Cited by
Voice Pathology Detection and Classification Using Convolutional Neural Network Model
Mohammed, M. A., Abdulkareem, K. H., Mostafa, S. A., Khanapi Abd Ghani, M., Maashi, M. S., Garcia-Zapirain, B., Oleagordia, I., Alhakami, H., & AL-Dhief, F. T. (2020) · Applied Sciences · doi:10.3390/app10113723 · Cited by 208
“The most common voice pathology databases are the Saarbruecken Voice Database (SVD) [9], Arabic Voice Pathology Database (AVPD) [10] and the Massachusetts Eye and Ear Infirmary Database (MEEI) [11].”
BackgroundA Survey on Machine Learning Approaches for Automatic Detection of Voice Disorders
Hegde, S., Shetty, S., Rai, S., & Dodderi, T. (2019) · Journal of Voice · doi:10.1016/j.jvoice.2018.07.014 · Cited by 193
“Al-nasheri et al, 59 in their paper, concentrated on developing an accurate and robust feature extraction for detecting and classifying voice pathologies by investigating different frequency bands using autocorrelation and entropy.”
Voice Pathology Detection Using Deep Learning on Mobile Healthcare Framework
Alhussein, M., & Muhammad, G. (2018) · IEEE Access · doi:10.1109/access.2018.2856238 · Cited by 189
Self-citationEEG-Based Pathology Detection for Home Health Monitoring
Muhammad, G., Hossain, M. S., & Kumar, N. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3020654 · Cited by 148
“Pathology can be detected using voice or other signals [3], [4].”
BackgroundSelf-citationAl-Dhief, F. T., Latiff, N. M. A., Malik, N. N. N. A., Salim, N. S., Baki, M. M., Albadr, M. A. A., & Mohammed, M. A. (2020) · IEEE Access · doi:10.1109/access.2020.2984925 · Cited by 131
Metadata
- Authors
- Al-Nasheri, A., Muhammad, G., Alsulaiman, M., Ali, Z., Malki, K. H., Mesallam, T. A., & Farahat Ibrahim, M.
- Affiliations
- King Saud University (SA)
- ORCID
- Venue
- IEEE Access
- Published
- 2018
- Volume
- 6
- Pages
- 6961-6974
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2609527102
- Cited by
- 174
- References
- 37
- Citations by year
- 2026: 9 · 2025: 18 · 2024: 18 · 2023: 28 · 2022: 30 · 2021: 21 · 2020: 19 · 2019: 15 · 2018: 16
- FWCI
- 10.15
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion)
- Ulster University Research Portal (Ulster University) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Deanship of Scientific Research at King Saud University through Research Group (RG-1437-018)
- Topics
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Phonocardiography and Auscultation Techniques
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- voice pathology detection, voice pathology classification, autocorrelation features, entropy features, frequency bands, sustained vowels, support vector machine
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.