Vocal Fold Pathology Assessment Using Mel-Frequency Cepstral Coefficients and Linear Predictive Cepstral Coefficients Features

Saldanha, Jennifer C.; Ananthakrishna, T.; Pinto, Rohan

doi:10.1166/jmihi.2014.1253

Cited by 27 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The popular features in this category are mel-frequency cepstral coefficients (MFCCs) [4], [15], [25] that utilize the principles of human auditory processing in the mel-scale and the decorrelating property of cepstrum. In addition, linear predictive cepstral coefficients (LPCCs) [21], [26], [27] and perceptual linear prediction (PLP) [4], [28] coefficients have been used in voice pathology detection. LPCCs capture the vocal tract system characteristics.…”

Section: Introductionmentioning

confidence: 99%

Analysis and Detection of Pathological Voice Using Glottal Source Features

Kadiri

Alku

2020

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Automatic detection of voice pathology enables objective assessment and earlier intervention for the diagnosis. This study provides a systematic analysis of glottal source features and investigates their effectiveness in voice pathology detection. Glottal source features are extracted using glottal flows estimated with the quasi-closed phase (QCP) glottal inverse filtering method, using approximate glottal source signals computed with the zero frequency filtering (ZFF) method, and using acoustic voice signals directly. In addition, we propose to derive mel-frequency cepstral coefficients (MFCCs) from the glottal source waveforms computed by QCP and ZFF to effectively capture the variations in glottal source spectra of pathological voice. Experiments were carried out using two databases, the Hospital Universitario Príncipe de Asturias (HUPA) database and the Saarbrücken Voice Disorders (SVD) database. Analysis of features revealed that the glottal source contains information that discriminates normal and pathological voice. Pathology detection experiments were carried out using support vector machine (SVM). From the detection experiments it was observed that the performance achieved with the studied glottal source features is comparable or better than that of conventional MFCCs and perceptual linear prediction (PLP) features. The best detection performance was achieved when the glottal source features were combined with the conventional MFCCs and PLP features, which indicates the complementary nature of the features.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis and Detection of Pathological Voice Using Glottal Source Features

Kadiri

Alku

2020

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Next, conventional and clinically interpretable [10]) acoustic features were usually computed prior to pathology detection [43,14,51]. The acoustic features such as multidimensional voice program parameters (MDVP) [4], mel-frequency cepstral coefficients (MFCC) [52], glottalto-noise excitation ratio (GNE) [42], etc. were usually extracted.…”

Section: Introductionmentioning

confidence: 99%

Towards robust voice pathology detection

Harár

Galáž

Alonso-Hernández

et al. 2018

Neural Comput & Applic

View full text Add to dashboard Cite

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 3 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 4 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.

show abstract

“…Mel frequency cepstral coefficients are used in various speech applications like speech recognition, vocal fold disease detection [12,13,14]. An MFCC calculation is a non-parametric modeling method and follows the human auditory perception system.…”

Section: Mel-frequency Cepstral Coefficients (Mfcc)mentioning

confidence: 99%

Speaker Identification using SVM during Oriya Speech Recognition

Saloni¹,

Sharma²,

Gupta³

2015

IJIGSP

View full text Add to dashboard Cite

Human speech signal is an acoustic wave, which conveys the information about the words or message being spoken, identity of the speaker, language spoken, the presence and type of speech pathologies, the physical and emotional state of the speaker. Speech under physical task stress shows variations from the speech in neutral state and thus degrades the speech system performance. In this paper we have characterized the voice samples under physical stress and the acoustic parameters are compared with the neutral state voice parameters. The traditional voice measures, glottal flow parameters, mel frequency cepstrum coefficients and energy in various frequency bands are used for this characterization. T-test is performed to check the statistical significance of parameters. Significant variations are noticed in the parameters under two states. Pitch, intensity, energy values are high for the physically stressed voice; On the other hand glottal parameter values get decreased. Cepstrum coefficients shift up from the coefficients of neutral state voice samples. Energy in lower frequency bands was more sensitive to physical stress. This study improves the performance of various speech processing applications by analyzing the unwanted effect of physical stress in voice.

show abstract

Vocal Fold Pathology Assessment Using Mel-Frequency Cepstral Coefficients and Linear Predictive Cepstral Coefficients Features

Cited by 27 publications

References 0 publications

Analysis and Detection of Pathological Voice Using Glottal Source Features

Analysis and Detection of Pathological Voice Using Glottal Source Features

Towards robust voice pathology detection

Speaker Identification using SVM during Oriya Speech Recognition

Contact Info

Product

Resources

About