Towards interpretable speech biomarkers: exploring MFCCs
Open accessPublished version of a preprint
Abstract
While speech biomarkers of disease have attracted increased interest in recent years, a challenge is that features derived from signal processing or machine learning approaches may lack clinical interpretability. As an example, Mel frequency cepstral coefficients (MFCCs) have been identified in several studies as a useful marker of disease, but are regarded as uninterpretable. Here we explore correlations between MFCC coefficients and more interpretable speech biomarkers. In particular we quantify the MFCC2 endpoint, which can be interpreted as a weighted ratio of low- to high-frequency energy, a concept which has been previously linked to disease-induced voice changes. By exploring MFCC2 in several datasets, we show how its sensitivity to disease can be increased by adjusting computation parameters.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
MFCCs present interpretability challenges due to their abstract and decorrelated nature.
“While MFCCs are also hand-engineered features, they present interpretability challenges due to their abstract and decorrelated nature [117].”
From Explainable and Interpretable AI for Voice and Speech Analysis in Clinical Care: Systematic Review (2026) · cites this paper as [117]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465 · see citing works
IEEE Transactions on Biomedical Engineering
(2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.10 · Cited by 1,412 · see citing works
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 · see citing works
Acoustic correlates of breathy vocal quality: dysphonic voices and continuous speech.
Hillenbrand, J., & Houde, R. A. (1996) · Journal of Speech, Language, and Hearing Research · doi:10.1044/jshr.3902.311 · Cited by 631 · see citing works
Introducing Parselmouth: A Python interface to Praat
Jadoul, Y., Thompson, B., & de Boer, B. (2018) · Journal of Phonetics · doi:10.1016/j.wocn.2018.07.001 · Cited by 512 · see citing works
Hlavnička, J., Čmejla, R., Tykalová, T., Šonka, K., Růžička, E., & Rusz, J. (2017) · Scientific Reports · doi:10.1038/s41598-017-00047-5 · Cited by 326 · see citing works
Godino-Llorente, J. I., Gomez-Vilda, P., & Blanco-Velasco, M. (2006) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2006.871883 · Cited by 322 · see citing works
Perceptual evaluation of voice quality and its correlation with acoustic measurements
Bhuta, T., Patrick, L. D., & Garnett, J. D. (2004) · Journal of Voice · doi:10.1016/j.jvoice.2003.12.004 · Cited by 288 · see citing works
Lipsmeier, F., Taylor, K. I., Kilchenmann, T., Wolf, D., Scotland, A., Schjodt‐Eriksen, J., Cheng, W., Fernandez‐Garcia, I., Siebourg‐Polster, J., Jin, L., et al. (2018) · Movement Disorders · doi:10.1002/mds.27376 · Cited by 266 · see citing works
Objective 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 212 · see citing works
Classification of speech dysfluencies with MFCC and LPCC features
Ooi, C. A., Hariharan, M., Yaacob, S., & Chee, L. S. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.07.065 · Cited by 174 · see citing works
Progressive Nonfluent Aphasia and Its Characteristic Motor Speech Deficits
Ogar, J., Dronkers, N., Brambati, S., Miller, B., & Gorno-Tempini, M. (2007) · Alzheimer Disease and Associated Disorders · doi:10.1097/wad.0b013e31815d19fe · Cited by 173 · see citing works
Voice changes in Parkinson’s disease: What are they telling us?
Ma, A., Lau, K. K., & Thyagarajan, D. E. (2020) · Journal of Clinical Neuroscience · doi:10.1016/j.jocn.2019.12.029 · Cited by 171 · see citing works
Major depressive disorder discrimination using vocal acoustic features
Taguchi, T., Tachikawa, H., Nemoto, K., Suzuki, M., Nagano, T., Tachibana, R., Nishimura, M., & Arai, T. (2017) · Journal of Affective Disorders · doi:10.1016/j.jad.2017.08.038 · Cited by 144 · see citing works
Voiceprints analysis using MFCC and SVM for detecting patients with Parkinson's disease
Benba, A., Jilbab, A., Hammouch, A., & Sandabad, S. (2015) · International Conference on Electrical and Information Technologies · doi:10.1109/eitech.2015.7163000 · Cited by 102 · see citing works
Vogel, A. P., Shirbin, C. A., Churchyard, A., & Stout, J. C. (2012) · Neuropsychologia · doi:10.1016/j.neuropsychologia.2012.09.011 · Cited by 94 · see citing works
Self-citationA Framework for Biomarkers of COVID-19 Based on Coordination of Speech-Production Subsystems
Quatieri, T. F., Talkar, T., & Palmer, J. S. (2020) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2020.2998051 · Cited by 94 · see citing works
Poole, M. L., Brodtmann, A., Darby, D., & Vogel, A. P. (2017) · Journal of Speech, Language, and Hearing Research · doi:10.1044/2016_jslhr-s-16-0140 · Cited by 84 · see citing works
Self-citationX-Vectors: New Quantitative Biomarkers for Early Parkinson's Disease Detection From Speech
Jeancolas, L., Petrovska‐Delacrétaz, D., Mangone, G., Benkelfat, B.-E., Corvol, J., Vidailhet, M., Lehéricy, S., & Benali, H. (2021) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2021.578369 · Cited by 75 · see citing works
Acoustic analysis of the effects of sustained wakefulness on speech
Vogel, A. P., Fletcher, J. M., & Maruff, P. T. (2010) · The Journal of the Acoustical Society of America · doi:10.1121/1.3506349 · Cited by 71 · see citing works
Self-citationClassification of Speech Dysfluencies Using LPC Based Parameterization Techniques
Hariharan, M., Chee, L. S., Ooi, C. A., & Yaacob, S. (2011) · Journal of Medical Systems · doi:10.1007/s10916-010-9641-6 · Cited by 66 · see citing works
Hawi, S., Alhozami, J., Alqahtani, R., et al. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104013 · Cited by 54 · see citing works
Motor speech signature of behavioral variant frontotemporal dementia: Refining the phenotype
Vogel, A. P., Poole, M. L., Pemberton, H., Caverlé, M. W. J., Boonstra, F. M. C., Low, E., Darby, D., & Brodtmann, A. (2017) · Neurology · doi:10.1212/wnl.0000000000004248 · Cited by 49 · see citing works
Self-citationMotor speech and non-motor language endophenotypes of Parkinson’s disease
Magee, M., Copland, D. A., & Vogel, A. P. (2019) · Expert Review of Neurotherapeutics · doi:10.1080/14737175.2019.1649142 · Cited by 44 · see citing works
Self-citationSimple and robust audio-based detection of biomarkers for Alzheimer's disease
Al-Hameed, S., Benaissa, M., & Christensen, H. (2016) · doi:10.21437/slpat.2016-6 · Cited by 42 · see citing works
Effect of Nasal Decongestion on Voice Spectrum of a Nasal Consonant-Vowel
Lee, G., Yang, C. C. H., Wang, C.-P., & Kuo, T. B. J. (2004) · Journal of Voice · doi:10.1016/j.jvoice.2004.03.002 · Cited by 32 · see citing works
McFee, B., McVicar, M., Nieto, O., et al. (2017) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.774759 · Cited by 30 · see citing works
A Cross-sectional Study of Perceptual and Acoustic Voice Characteristics in Healthy Aging
Schultz, B. G., Rojas, S., John, M. S., Kefalianos, E., & Vogel, A. P. (2021) · Journal of Voice · doi:10.1016/j.jvoice.2021.06.007 · Cited by 22 · see citing works
Self-citationA Tutorial Review on Clinical Acoustic Markers in Speech Science
Schultz, B. G., & Vogel, A. P. (2022) · Journal of Speech Language and Hearing Research · doi:10.1044/2022_jslhr-21-00647 · Cited by 13 · see citing works
Self-citationCepstral Derivatives in MFCCs for Emotion Recognition
(2019) · doi:10.1109/siprocess.2019.8868573 · Cited by 11 · see citing works
Voice Biomarkers of Recovery From Acute Respiratory Illness
Tracey, B., Patel, S., Zhang, Y., Chappie, K., Volfson, D., Parisi, F., Adans-Dester, C., Bertacchi, F., Bonato, P., & Wacnik, P. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3137050 · Cited by 10 · see citing works
Self-citation7th Workshop on Speech and Language Processing for Assistive Technologies (SLPAT 2016)
Christensen, H., Portet, F., Quatieri, T. F., Rudzicz, F., & Vertanen, K. (2016) · doi:10.21437/slpat.2016 · Cited by 9 · see citing works
Adults with a history of recreational cannabis use have altered speech production
Vogel, A. P., Pearson-Dennett, V., Magee, M., Wilcox, R. A., Esterman, A., Thewlis, D., White, J. M., & Todd, G. (2021) · Drug and Alcohol Dependence · doi:10.1016/j.drugalcdep.2021.108963 · Cited by 8 · see citing works
Self-citationCLAC: A Speech Corpus of Healthy English Speakers
Haulcy, R., & Glass, J. R. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1810 · Cited by 7 · see citing works
Self-citationVogel, A. P., & Reece, H. (2021) · Routledge eBooks · doi:10.4324/9780429320903-18 · Cited by 2 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Developing digital health technologies for frontotemporal degeneration
Nevler, N., Niehoff, D., Gleixner, A. M., Dodge, S., Vogel, A. P., Hill, D. L., Ducharme, S., Staffaroni, A. M., Yunusova, Y., Au, R., et al. (2025) · Alzheimer's & Dementia · doi:10.1002/alz.70082 · Cited by 7 · see citing works
Self-citationGlobal vs. segmental acoustic features for dysarthria assessment in motor neuron diseases
Attia, M., Simmatis, L., Sejdic, E., & Yunusova, Y. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.111291
Explainable and Interpretable AI for Voice and Speech Analysis in Clinical Care: Systematic Review
Ebraheem, M., Toghranegar, J., Bridge2AI-Voice Consortium, Bensoussan, Y., & Templeton, J. M. (2026) · Journal of Medical Internet Research · doi:10.2196/83790
- Authors
- Tracey, B., Volfson, D., Glass, J., Haulcy, R., Kostrzebski, M., Adams, J., Kangarloo, T., Brodtmann, A., Dorsey, E. R., & Vogel, A.
- Affiliations
- MIT Computer Science and Artificial Intelligence Laboratory (US)
- University of Rochester Medicine (US)
- The University of Melbourne (AU)
- Corresponding author
- Tracey, Brian
- ORCID
- Venue
- Scientific Reports
- Published
- 2023-12-21
- Volume
- 13
- Issue
- 1
- Pages
- 22787-22787
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC10733367
- OpenAlex
- W4390030622
- Cited by
- 46
- References
- 35
- Citations by year
- 2026: 18 · 2025: 19 · 2024: 8 · 2023: 1
- FWCI
- 8.13
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Scientific Reports (publishedVersion, cc-by)
- Research Square (acceptedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Takeda Pharmaceuticals U.S.A.
- Biogen
- members of the Critical Path for Parkinson’s Consortium 3DT Initiative, Stage 2
- Topics
- Health Sciences › Medicine › Physiology › Voice and Speech Disorders
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Phonocardiography and Auscultation Techniques
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Keywords
- speech biomarkers, Mel-frequency cepstral coefficients, interpretable features, voice change, disease detection, speech processing, parameter sensitivity
- MeSH terms
- Signal Processing, Computer-Assisted, Speech, Speech Acoustics
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
