The automatic detection of heart failure using speech signals. (September 2021)

• Record Type: Journal Article
• Authors: Kiran Reddy, M.; Helkkula, Pyry; Madhu Keerthana, Y.; Kaitue, Kasimir; Minkkinen, Mikko; Tolppanen, Heli; Nieminen, Tuomo; Alku, Paavo
• Is Part Of: Computer speech & language. Volume 69(2021)
• Publication Date: 2021-09
• Subjects: Heart failure -- Mel-frequency cepstral coefficients -- Glottal source parameters -- Support vector machines -- Extra tree -- AdaBoost -- Neural networks; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2021.101205
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: For the first time, automatic detection of heart failure (HF) from speech is studied. Both vocal tract and glottal source parameters are used in feature extraction. Four machine learning algorithms are used as classifiers. Applying Feature selection on glottal + vocal tract features improved classification accuracy. Among the classifiers, the neural network gave the best performance. Abstract: Heart failure (HF) is a major global health concern and is increasing in prevalence. It affects the larynx and breathing – thereby the quality of speech. In this article, we propose an approach for the automatic detection of people with HF using the speech signal. The proposed method explores mel-frequency cepstral coefficient (MFCC) features, glottal features, and their combination to distinguish HF from healthy speech. The glottal features were extracted from the voice source signal estimated using glottal inverse filtering. Four machine learning algorithms, namely, support vector machine, Extra Tree, AdaBoost, and feed-forward neural network (FFNN), were trained separately for individual features and their combination. It was observed that the MFCC features yielded higher classification accuracies compared to glottal features. Furthermore, the complementary nature of glottal features was investigated by combining these features with the MFCC features. Our results show that the FFNN classifier trained using a reduced set of glottal + MFCC features achieved the best overall performance in both speaker-dependent and speaker-independent scenarios.