Interpretable phonological features for clinical applications
Abstract
Instrumental analysis of speech sometimes complements subjective evaluations in speech and language therapy; however, apart from elemental speech features such as pitch and formant statistics, higher dimensional spectral features are rarely used in practice because they are clinically uninterpretable. While these features are likely to somehow be related to clinical intervention, this relationship remains to be determined. This paper uses artificial recurrent neural networks to map high-dimensional spectral features into phonological features that are easily interpretable and provide fine-resolution information regarding articulation quality. The evaluation on a dysarthric speech data set shows strong correlation between the phonological feature measures and perceptual ratings. To increase clinical utility, we provide a new way to visualize phonological disturbances that provides clinicians with actionable information about intervention strategies.
Integrity signals
Registry
Cites
Statistics
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?
Word embeddings are based on the distributional hypothesis that a word's meaning comes from its contextual usage.
“Word embeddings are motivated by the distributional hypothesis in linguistics, a concept proposed by English linguist John R. Firth who famously stated “You shall know a word by the company it keeps” [83], i.e. that the inherent meaning of words is derived from their contextual usage in natural language.”
From A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorders (2020) · cites this paper as [83]
Despite efforts to position MFCCs as vocal biomarkers, they largely obscure the internal workings of deep models and contribute to the opacity of clinical audio systems.
“Despite efforts to position MFCCs as vocal biomarkers, they largely obscure the internal workings of deep models and contribute to the opacity of clinical audio systems [118].”
From Explainable and Interpretable AI for Voice and Speech Analysis in Clinical Care: Systematic Review (2026) · cites this paper as [118]
Cites
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · see citing works
Fundamentals of speech recognition
Rabiner, L. R., & Juang, B.-H. F. (1993) · Cited by 7,680 · see citing works
On the generalized distance in statistics
Mahalanobis, P. C. (1936) · DOAJ (DOAJ: Directory of Open Access Journals) · Cited by 6,068 · see citing works
Perceptual linear predictive (PLP) analysis of speech
Heřmanský, H. (1990) · The Journal of the Acoustical Society of America · doi:10.1121/1.399423 · Cited by 2,550 · see citing works
TIMIT Acoustic-Phonetic Continuous Speech Corpus
Garofolo, J. S., Lamel, L. F., Fisher, W. M., Pallett, D. S., Dahlgren, N. L., Zue, V. W., & Fiscus, J. G. (2020) · Americanae (AECID Library) · doi:10.35111/17gk-bn40 · Cited by 2,509 · see citing works
Motor Speech Disorders: Substrates, Differential Diagnosis, and Management
Duffy, J. R. (1995) · Cited by 1,892 · see citing works
Garvin, P. L. (1953) · Language · doi:10.2307/409957 · Cited by 1,168 · see citing works
Speaker identification on the SCOTUS corpus
Yuan, J., & Liberman, M. (2008) · The Journal of the Acoustical Society of America · doi:10.1121/1.2935783 · Cited by 600 · see citing works
Taylor, P. (2009) · Cambridge University Press eBooks · doi:10.1017/cbo9780511816338 · Cited by 549 · see citing works
A new model of LPC excitation for producing natural-sounding speech at low bit rates
Atal, B. S., & Remde, J. (2005) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.1982.1171649 · Cited by 510 · see citing works
A mixed excitation LPC vocoder model for low bit rate speech coding
McCree, A. V., & Barnwell, T. P., III (1995) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.397089 · Cited by 314 · see citing works
Primitives-based evaluation and estimation of emotions in speech
Grimm, M., Kroschel, K., Mower, E., & Narayanan, S. S. (2007) · Speech Communication · doi:10.1016/j.specom.2007.01.010 · Cited by 291 · see citing works
Zen, H., & Sak, H. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178816 · Cited by 266 · see citing works
Toward an acoustic typology of motor speech disorders
Kent, R. D., & Kim, Y. (2003) · Clinical Linguistics & Phonetics · doi:10.1080/0269920031000086248 · Cited by 246 · see citing works
Learning a better representation of speech soundwaves using restricted boltzmann machines
Jaitly, N., & Hinton, G. (2011) · 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2011.5947700 · Cited by 231 · cited 1× · see citing works
“Recently with the development of deep learning, the output or the intermediate output of artificial neural networks can also serve as acoustic features for certain tasks [9][10][11].”
BackgroundDetection of phonological features in continuous speech using neural networks
King, S., & Taylor, P. (2000) · Computer Speech & Language · doi:10.1006/csla.2000.0148 · Cited by 196 · see citing works
Quantifying Speech Rhythm Abnormalities in the Dysarthrias
Liss, J., White, L., Mattys, S. L., Lansford, K. L., Lotto, A. J., Spitzer, S. M., & Caviness, J. N. (2009) · Journal of Speech Language and Hearing Research · doi:10.1044/1092-4388(2009/08-0208 · Cited by 177 · see citing works
Self-citationIntroducing CURRENNT: the Munich open-source CUDA recurrent neural network toolkit
Weninger, F. J., Bergmann, J. M., & Schuller, B. W. (2015) · Spiral (Imperial College London) · Cited by 161 · see citing works
Robustness in Automatic Speech Recognition: Fundamentals and Applications
Junqua, J.-C., & Haton, J. (1995) · Cited by 147 · see citing works
Feature analysis for automatic detection of pathological speech
Dibazar, A. A., Narayanan, S. S., & Berger, T. W. (2003) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2002.1134447 · Cited by 137 · see citing works
Single-channel speech separation with memory-enhanced recurrent neural networks
Weninger, F. J., Eyben, F., & Schuller, B. W. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854294 · Cited by 128 · see citing works
Automated Intelligibility Assessment of Pathological Speech Using Phonological Features
Middag, C., Martens, J., Nuffelen, G. V., & Bodt, M. S. D. (2009) · EURASIP Journal on Advances in Signal Processing · doi:10.1155/2009/629030 · Cited by 94 · see citing works
Convolutive Bottleneck Network features for LVCSR
Vesely, K., Karafiát, M., & Grézl, F. (2011) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2011.6163903 · Cited by 78 · see citing works
Voice conversion by codebook mapping of line spectral frequencies and excitation spectrum
Arslan, L. M., & Talkin, D. T. (1997) · European Conference on Speech Communication and Technology (Eurospeech) · doi:10.21437/eurospeech.1997-383 · Cited by 75 · see citing works
Jiao, Y., Tu, M., Berisha, V., et al. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-1148 · Cited by 61 · see citing works
Self-citationFeature 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 · see citing works
Phonological vocoding using artificial neural networks
Cerňak, M., Potard, B., & Garner, P. N. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178891 · Cited by 25 · see citing works
On compressibility of neural network phonological features for low bit rate speech coding
Asaei, A., Cerňak, M., & Bourlard, H. A. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-167 · Cited by 16 · see citing works
Online speaking rate estimation using recurrent neural networks
Jiao, Y., Tu, M., Berisha, V., & Liss, J. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472678 · Cited by 15 · see citing works
Self-citationAnalysis of Dysarthric Speech using Distinctive Feature Recognition
Wong, K. H., Yeung, Y. T., Wong, P. C. M., Levow, G., & Meng, H. M. L. (2015) · Workshop on Speech and Language Processing for Assistive Technologies · doi:10.18653/v1/w15-5115 · Cited by 6 · see citing works
Exploring articulatory characteristics of Cantonese dysarthric speech using distinctive features
Wong, K. H., Yeung, W. S., Yeung, Y. T., & Meng, H. M. L. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472928 · Cited by 4 · see citing works
Removing data with noisy responses in regression analysis
Wisler, A. A., Berisha, V., Ramamurthy, K. N., Spanias, A., & Liss, J. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178334 · Cited by 2 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorders
Voleti, R., Liss, J. M., & Berisha, V. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2952087 · Cited by 96 · see citing works
Self-citationExplainable 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
- Jiao, Y., Berisha, V., & Liss, J.
- Affiliations
- Arizona State University (US)
- Venue
- 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2017-03
- Pages
- 5045-5049
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2672120608
- Cited by
- 13
- References
- 32
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 1 · 2023: 3 · 2021: 1 · 2020: 1 · 2019: 2 · 2018: 1
- FWCI
- 6.93
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- Topics
- Health Sciences › Medicine › Physiology › Voice and Speech Disorders
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Phonetics and Phonology Research
- Keywords
- phonological features, spectral properties, dysarthria, speech perception, recurrent neural networks, feature mapping, perceptual ratings, speech therapy
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
