Automatic Detection of Laryngeal Pathologies in Records of Sustained Vowels by Means of Mel-Frequency Cepstral Coefficient Parameters and Differentiation of Patients by Sex
The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
Mel-frequency cepstral coefficients (MFCC) have traditionally been used in speaker identification applications. Their use has been extended to speech quality assessment for clinical applications during the last few years. While the significance of such parameters for such an application may not seem clear at first thought, previous research has demonstrated their robustness and statistical significance and, at the same time, their close relationship with glottal noise measurements. This paper includes a review of this parameterization scheme and it analyzes its performance for voice analysis when patients are differentiated by sex. While it is of common use for establishing normative values for traditional voice descriptors (e.g. pitch, jitter, formants), differentiation by sex had not been tested yet for cepstral analysis of voice with clinical purposes. This paper shows that the automatic detection of laryngeal pathology on voice records based on MFCC can significantly improve its performance by means of this prior differentiation by sex.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“The Log-Mel scale mimics human auditory perception, closely aligning with subjective pitch sensation and faithfully reflecting acoustic physical properties (47).”
From A deep learning approach for acoustic-based identification of muscle tension dysphonia and spasmodic dysphonia (2026) · cites this paper as [47]
Citations
Cites
Praat: Doing Phonetics by Computer
(2011) · Ear & Hearing · doi:10.1097/aud.0b013e31821473f7 · Cited by 7,863
Discrete-Time Processing of Speech Signals
Deller, J. R., Hansen, J. H. L., & Proakis, J. G. (1999) · Institute of Electrical and Electronics Engineers eBooks · doi:10.1109/9780470544402 · Cited by 2,458 · cited 2×
“After splitting the voice signal in frames, each frame undergoes a discrete Fourier transform (DFT), hence computing a short-term DFT of each voice record [31] .”
MethodSpeaker recognition: a tutorial
Campbell, J. P. (1997) · Proceedings of the IEEE · doi:10.1109/5.628714 · Cited by 1,629 · cited 1×
“When building such templates, it is common to differentiate between male and female speakers, since such differentiation has shown to improve identification re-sults [22] .”
BackgroundThe DET curve in assessment of detection task performance
Martin, A., Doddington, G., Kamm, T., Ordowski, M., & Przybocki, M. (1997) · 5th European Conference on Speech Communication and Technology (Eurospeech 1997) · doi:10.21437/eurospeech.1997-504 · Cited by 1,384 · cited 1×
“Bearing this in mind, the first analysis that has been carried out consists in studying the sex-specific distribution of the most significant MFCC for normal and pathological speech frames within the available database. Figure 3 shows the resulting experimental probability density functions (fig. 3 a). Also, the error…”
A Tutorial on Text-Independent Speaker Verification
Bimbot, F., Bonastre, J.-F., Fredouille, C., Gravier, G., Magrin-Chagnolleau, I., Meignier, S., Merlin, T., Ortega-García, J., Petrovska-Delacrétaz, D., & Reynolds, D. A. (2004) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/s1110865704310024 · Cited by 798 · cited 2×
“A common way to decide is to base the decision on the log-likelihood ratio ( LLR i ) that relates both estimates [35] : However, for a voice record consisting of N frames, the decision should be made at the record level (in fact, all frames of a record belong to the same voice).”
BackgroundSelf-citationGodino-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 1×
“Statistical confirmation of this can be found in Godino-Llorente et al. [”
BackgroundSelf-citationComparative Evaluation of Various MFCC Implementations on the Speaker Verification Task
Ganchev, T. D., Fakotakis, N., & Kokkinakis, G. C. (2007) · Cited by 305
Godino-Llorente, J. I., & Gomez-Vilda, P. (2004) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2003.820386 · Cited by 264
Self-citationIdentification of Pathological Voices Using Glottal Noise Measures
Parsa, V., & Jamieson, D. G. (2000) · Journal of Speech, Language, and Hearing Research · doi:10.1044/jslhr.4302.469 · Cited by 182
Objective Voice Analysis for Dysphonic Patients
Yu, P., Ouaknine, M., Revis, J., & Giovanni, A. (2001) · Journal of Voice · doi:10.1016/s0892-1997(01)00053-4 · Cited by 162
Discrimination of pathological voices using a time-frequency approach
Umapathy, K., Krishnan, S., Parsa, V., & Jamieson, D. G. (2005) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2004.842962 · Cited by 149 · cited 1×
“…; • introducing alternative parameterization schemes that either capture different features of voice [13] or allow for processing of running speech [14] , thus achieving better performance; • introducing alternative parameters that are more robust against noise and other distortions [15] and avoid…”
BackgroundAcoustic model and evaluation of pathological voice production
Deliyski, D. D. (1993) · 3rd European Conference on Speech Communication and Technology (Eurospeech 1993) · doi:10.21437/eurospeech.1993-445 · Cited by 138 · cited 3×
“…assessment among health care activities should increase in the near future and the development of computer-aided software for voice assessment [2–4] should not only support such growth, but also help assessment tasks to get out of the clinics and closer to people’s residences and working…”
BackgroundMethodBoyanov, B., & Hadjitodorov, S. (1997) · IEEE Engineering in Medicine and Biology Magazine · doi:10.1109/51.603651 · Cited by 137
Vocal Tract Resonance Analysis of Aging Voice Using Long-Term Average Spectra
Linville, S. E., & Rens, J. (2001) · Journal of Voice · doi:10.1016/s0892-1997(01)00034-0 · Cited by 137 · cited 1×
“From a medical point of view, there are factors that support this distinction, such as age [24] and hormonal chang-D es [25] .”
BackgroundAutomatic Detection of Pathologies in The Voice by HOS Based Parameters
Alonso, J. B., de Leon, J., Alonso, I., & Ferrer, M. A. (2001) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/s1110865701000336 · Cited by 108 · cited 1×
“• introducing alternative parameterization schemes that either capture different features of voice [”
BackgroundInfluence of Age and Gender on the Dysphonia Severity Index
Hakkesteegt, M. M., Brocaar, M. P., Wieringa, M. H., & Feenstra, L. (2006) · Folia Phoniatrica et Logopaedica · doi:10.1159/000093183 · Cited by 91
Horáček, J., Laukkanen, A.-M., Šidlof, P., Murphy, P., & Švec, J. G. (2009) · Folia Phoniatrica et Logopaedica · doi:10.1159/000219949 · Cited by 60 · cited 1×
“The modelling work reported by Horáček et al. [26] demonstrates that the anatomic and physiological differences between men and women also result in a different risk of developing some vocal fold pathologies.”
MethodAn integrated tool for the diagnosis of voice disorders
Godino-Llorente, J. I., Sáenz-Lechón, N., Osma-Ruiz, V., Aguilera-Navarro, S., & Gómez‐Vilda, P. (2005) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2005.04.014 · Cited by 55
Self-citationApplication of automatic speaker recognition techniques to pathological voice assessment (dysphonia)
Fredouille, C., Pouchoulin, G., Bonastre, J.-F., Azzarello, M., Giovanni, A., & Ghio, A. (2005) · Interspeech (USB) · doi:10.21437/interspeech.2005-90 · Cited by 52 · cited 1×
“…of combining different kinds of parameters [11] and incorporating pattern classification techniques used in other applications of speech analysis [12] ; • introducing alternative parameterization schemes that either capture different features of voice [13] or allow for processing of running…”
MethodSelf-citationMa, E., & Yiu, E. M. ‐. (2005) · Folia Phoniatrica et Logopaedica · doi:10.1159/000081960 · Cited by 49 · cited 2×
“This difficulty has specifically been observed in the analysis of dysphonic voices [17] .”
BackgroundAcoustic and Perceptual Evaluation of Voice and Speech Quality
Finizia, C. A., Dotevall, H., Lundström, E., & Lindström, J. (1999) · Archives of Otolaryngology - Head and Neck Surgery · doi:10.1001/archotol.125.2.157 · Cited by 40
Feature analysis of pathological speech signals using local discriminant bases technique
Umapathy, K., & Krishnan, S. (2005) · Medical & Biological Engineering & Computing · doi:10.1007/bf02344726 · Cited by 35 · cited 1×
“It must be noted that while the performance of automatic pathology detection decreases when patients are differentiated by sex [27] , the herein proposed scheme involves introducing ‘a priori’ knowledge about sex in order to improve pathology detection.”
MethodBoyanov, B., Ivanov, T., Hadjitodorov, S. T., & Chollet, G. (1993) · Electronics Letters · doi:10.1049/el:19931281 · Cited by 31 · cited 1×
“…features of voice [13] or allow for processing of running speech [14] , thus achieving better performance; • introducing alternative parameters that are more robust against noise and other distortions [15] and avoid the need of pitch detection, which is a difficult task in many circumstances [16] .”
BackgroundJackson-Menaldi, M. C. (2002) · Cited by 28
Frequency study for the characterization of the dysphonic voices
Pouchoulin, G., Fredouille, C., Bonastre, J.-F., Ghio, A., & Giovanni, A. (2007) · Interspeech (USB) · doi:10.21437/interspeech.2007-386 · Cited by 27 · cited 1×
“This transforms the signal into frequency domain. The left graph of figure 1 shows (in gray) the modulus of the DFT corresponding to one speech frame. It is well known that this function results from the superposition of two effects: the rapid variations of the graph, coming from the quasi-periodic vibrations of the v…”
Self-citationMuñoz, R. F., Lechón, N. S., Godino-Llorente, J. I., Ruiz, V. O., & Gómez‐Vilda, P. (2008) · Cited by 15
Self-citationFraile, R., Sáenz-Lechón, N., Godino-Llorente, J. I., Osma-Ruiz, V., & Fredouille, C. (2009) · International Conference on Bio-inspired Systems and Signal Processing · doi:10.5220/0001534200410048 · Cited by 12
Self-citationComplementary approaches for voice disorder assessment
Bonastre, J.-F., Fredouille, C., Ghio, A., Giovanni, A., Pouchoulin, G., Révis, J., Teston, B., & Yu, P. (2007) · Interspeech (USB) · doi:10.21437/interspeech.2007-385 · Cited by 9 · cited 1×
“Additionally, the objective nature of computer-based assessment algorithms has the potential advantage over human-based perceptual evaluation of requiring much less evaluation time and cost in human resources [5] .”
BackgroundSelf-citationPerrin, E., Berger-Vachon, C., Kauffmann, I., & Collet, L. (1997) · Medical & Biological Engineering & Computing · doi:10.1007/bf02534091 · Cited by 4 · cited 1×
“In medical practice, the values of acoustic parameters extracted from voice have been found to be highly correlated with the presence of some laryngeal pathologies [9] , thus confirming the previously mentioned assumption.”
Result
Cited by
Novel Speech Signal Processing Algorithms for High-Accuracy Classification of Parkinson’s Disease
Tsanas, A., Little, M. A., McSharry, P. E., Spielman, J., & Ramig, L. O. (2012) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2012.2183367 · Cited by 732
Tsanas, A., Little, M. A., McSharry, P. E., & Ramig, L. O. (2011) · Journal of The Royal Society Interface · doi:10.1098/rsif.2010.0456 · Cited by 323
Detection of Pathological Voice Using Cepstrum Vectors: A Deep Learning Approach
Fang, S.-H., Tsao, Y., Hsiao, M.-J., Chen, J.-Y., Lai, Y.-H., Lin, F.-C., & Wang, C.-T. (2019) · Journal of Voice · doi:10.1016/j.jvoice.2018.02.003 · Cited by 278
“Meanwhile, other work applied neural networks to classify MFCC features(9) and showed that the performance can be improved by differentiating the speaker’s gender.(10) Combining MFCCs and other acoustic features, Arias-Londono et al developed a multistaged classifier and effectively increased the accuracy to 98%.”
BackgroundResultInfluentialObjective Automatic Assessment of Rehabilitative Speech Treatment in Parkinson's Disease
Tsanas, A., Little, M. A., Fox, C., & Ramig, L. O. (2014) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2013.2293575 · Cited by 213
Kim, H., Jeon, J., Han, Y. J., Joo, Y., Lee, J., Lee, S., & Im, S. (2020) · Journal of Clinical Medicine · doi:10.3390/jcm9113415 · Cited by 97
“Despite our results favoring the 1D-CNN, due to the uneven gender distribution in laryngeal cancer, the gender composition of the data should be considered with caution when developing future deep learning algorithms since the female voice has broader distributions in cepstral domain analysis [29].”
Result
Metadata
- Authors
- Fraile, R., Sáenz-Lechón, N., Godino-Llorente, J. I., Osma-Ruiz, V., & Fredouille, C.
- Affiliations
- Universidad Politécnica de Madrid (ES)
- Université d'Avignon et des Pays de Vaucluse (FR)
- Venue
- Folia Phoniatrica et Logopaedica
- Publisher
- S. Karger AG
- Published
- 2009
- Volume
- 61
- Issue
- 3
- Pages
- 146-152
- ISSN
- 0015-5705 (ISSN-L)
- 1021-7762
- 1421-9972
- OpenAlex
- W2055387057
- Cited by
- 62
- References
- 29
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 2 · 2023: 3 · 2022: 3 · 2021: 6 · 2020: 4 · 2019: 6 · 2018: 5 · 2017: 5 · 2016: 2 · 2015: 4 · 2014: 2 · 2013: 5 · 2012: 3
- FWCI
- 1.99
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.karger.com/Services/SiteLicenses (vor)
- www.karger.com/Services/SiteLicenses (tdm)
- Locations
- Folia Phoniatrica et Logopaedica (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Phonocardiography and Auscultation Techniques
- Keywords
- laryngeal diseases, Mel-frequency cepstral coefficients, sustained vowels, sex differences, voice analysis, speech quality assessment, voice disorders, cepstral analysis
- MeSH terms
- Adult, Electronic Data Processing, Female, Humans, Laryngeal Diseases, Male, Middle Aged, Phonetics, Probability, Sex Characteristics, Sound Spectrography, Speech, Neural Networks, Computer, Young Adult
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.