Towards robust voice pathology detection: Investigation of supervised deep learning, gradient boosting, and anomaly detection approaches across four databases
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Automatic objective non-invasive detection of pathological voice based on computerized analysis of acoustic signals can play an important role in early diagnosis, progression tracking, and even effective treatment of pathological voices. In search towards such a robust voice pathology detection system, we investigated three distinct classifiers within supervised learning and anomaly detection paradigms. We conducted a set of experiments using a variety of input data such as raw waveforms, spectrograms, mel-frequency cepstral coefficients (MFCC), and conventional acoustic (dysphonic) features (AF). In comparison with previously published works, this article is the first to utilize combination of four different databases comprising normophonic and pathological recordings of sustained phonation of the vowel /a/ unrestricted to a subset of vocal pathologies. Furthermore, to our best knowledge, this article is the first to explore gradient-boosted trees and deep learning for this application. The following best classification performances measured by F1 score on dedicated test set were achieved: XGBoost (0.733) using AF and MFCC, DenseNet (0.621) using MFCC, and Isolation Forest (0.610) using AF. Even though these results are of exploratory character, conducted experiments do show promising potential of gradient boosting and deep learning methods to robustly detect voice pathologies.
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.
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
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008) · 2008 Eighth IEEE International Conference on Data Mining · doi:10.1109/icdm.2008.17 · Cited by 6,601 · cited 1×
“In this case, we chose Isolation Forest [34,35] classifier implemented in scikit-learn library [48] (version 0.19.1).”
MethodInfluentialPimentel, M. A. F., Clifton, D. A., Clifton, L., & Tarassenko, L. (2014) · Signal Processing · doi:10.1016/j.sigpro.2013.12.026 · Cited by 1,649 · cited 1×
“In addition, we presume that use of deep learning methods for novelty detection such as deep autoen-coder [49] for modelling the normophonic voice could be an interesting idea for future investigation with prospect to identify even disordered voices that are sparsely distributed across databases.”
BackgroundPrinciples of Voice Production
Titze, I. R., & Martin, D. W. (1998) · The Journal of the Acoustical Society of America · doi:10.1121/1.424266 · Cited by 1,643
The Place of Inter-Rater Reliability in Qualitative Research: An Empirical Study
Armstrong, D., Gosling, A., Weinman, J., & Marteau, T. (1997) · Sociology · doi:10.1177/0038038597031003015 · Cited by 1,008
Al-Nasheri, A., Muhammad, G., Alsulaiman, M., Ali, Z., Malki, K. H., Mesallam, T. A., & Farahat Ibrahim, M. (2018) · IEEE Access · doi:10.1109/access.2017.2696056 · Cited by 174 · cited 2×
“98 (SVD) Al-nasheri 2017 [3] MEEI, SVD, AVPD /a/ SVM 99.”
BackgroundAmami, R., & Smiti, A. (2017) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2016.08.021 · Cited by 63
Cited by
Zhang, J., Wu, J., Qiu, Y., Song, A., Li, W., Li, X., & Liu, Y. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106517 · Cited by 69
“However, the application of speech technology only depends on the patient ’ s speech and a pre-training algorithm model incorporating medical experience, which is more objective than the traditional methods [192].”
A novel hybrid model integrating MFCC and acoustic parameters for voice disorder detection
Verma, V., Benjwal, A., Chhabra, A., Singh, S. K., Kumar, S., Gupta, B. B., Arya, V., & Chui, K. T. (2023) · Scientific Reports · doi:10.1038/s41598-023-49869-6 · Cited by 55
Lee, J. B., & Lee, H. G. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106014 · Cited by 15
A multi-stage transfer learning strategy for diagnosing a class of rare laryngeal movement disorders
Yao, Y., Powell, M., White, J., Feng, J., Fu, Q., Zhang, P., & Schmidt, D. C. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107534 · Cited by 10
Toward Real-World Voice Disorder Classification
Kuo, H.-C., Hsieh, Y.-P., Tseng, H.-H., Wang, C.-T., Fang, S.-H., & Tsao, Y. (2023) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2023.3270532 · Cited by 10
Metadata
- Authors
- Harar, P., Galaz, Z., Alonso-Hernandez, J. B., Mekyska, J., Burget, R., & Smekal, Z.
- Venue
- Neural Computing and Applications
- Published
- 2018-04-04
- Volume
- 32
- Issue
- 20
- Pages
- 15747-15757
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W2959813266
- Cited by
- 68
- References
- 7
- FWCI
- 1.63
- Type
- journal article
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Towards robust voice pathology detection: Investigation of supervised deep learning, gradient boosting, and anomaly detection approaches across four databases. https://app.cochat.ai/papers/10.1007/s00521-018-3464-7
- The paper
- Harar, P., Galaz, Z., Alonso-Hernandez, J. B., Mekyska, J., Burget, R., & Smekal, Z. (2020). Towards robust voice pathology detection: Investigation of supervised deep learning, gradient boosting, and anomaly detection approaches across four databases. Neural Computing and Applications. https://doi.org/10.1007/s00521-018-3464-7
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.