Glottal Source Information for Pathological Voice Detection
Authors:
Open Access
- 6 April 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 67745-67755
Abstract
Automatic methods for the detection of pathological voice from healthy speech can be considered as potential clinical tools for medical treatment. This study investigates the effectiveness of glottal source information in the detection of pathological voice by comparing the classical pipeline approach to the end-to-end approach. The traditional pipeline approach consists of a feature extractor and a separate classifier. In the former, two sets of glottal features (computed using the quasi-closed phase glottal inverse filtering method) are used together with the widely used openSMILE features. Using both the glottal and openSMILE features extracted from voice utterances and the corresponding healthy/pathology labels, support vector machine (SVM) classifiers are trained. In building end-to-end systems, both raw speech signals and raw glottal flow waveforms are used to train two deep learning architectures: (1) a combination of convolutional neural network (CNN) and multilayer perceptron (MLP), and (2) a combination of CNN and long short-term memory (LSTM) network. Experiments were carried out using three publicly available databases, including dysarthric (the UA-Speech database and the TORGO database) and dysphonic voices (the UPM database). The performance analysis of the detection system based on the traditional pipeline approach showed best results when the glottal features were combined with the baseline openSMILE features. The results of the end-to-end approach indicated higher accuracies (about 2-3%improvement in all three databases) when glottal flow was used as the raw time-domain input (87.93 % for UA-Speech, 81.12 % for TORGO and 76.66 % for UPM) compared to using raw speech waveform (85.12 % for UA-Speech, 78.83 % for TORGO and 73.71 % for UPM). The evaluation of both approaches demonstrate that automatic detection of pathological voice from healthy speech benefits from using glottal source information.Keywords
Funding Information
- Research Council of Finland (312490)
This publication has 68 references indexed in Scilit:
- Variability in the relationships among voice quality, harmonic amplitudes, open quotient, and glottal area waveform shape in sustained phonationThe Journal of the Acoustical Society of America, 2012
- Categorizing Normal and Pathological Voices: Automated and Perceptual CategorizationJournal of Voice, 2011
- The TORGO database of acoustic and articulatory speech from speakers with dysarthriaLanguage Resources and Evaluation, 2011
- On combining information from modulation spectra and mel-frequency cepstral coefficients for automatic detection of pathological voicesLogopedics Phoniatrics Vocology, 2010
- Speech technology‐based assessment of phoneme intelligibility in dysarthriaInternational Journal of Language & Communication Disorders, 2009
- Glottal Source biometrical signature for voice pathology detectionSpeech Communication, 2009
- Testing objective measures of motor impairment in early Parkinson's disease: Feasibility study of an at‐home testing deviceMovement Disorders, 2009
- Emotions in Vowel Segments of Continuous Speech: Analysis of the Glottal Flow Using the Normalised Amplitude QuotientPhonetica, 2006
- Vocal quality factors: Analysis, synthesis, and perceptionThe Journal of the Acoustical Society of America, 1991
- Clinical aspects of spasmodic dysphonia.Journal of Neurology, Neurosurgery & Psychiatry, 1978