On the design of automatic voice condition analysis systems. Part II: Review of speaker recognition techniques and study on the effects of different variability factors. (February 2019)

• Record Type: Journal Article
• Authors: Gómez-García, J.A.; Moro-Velázquez, L.; Godino-Llorente, J.I.
• Is Part Of: Biomedical signal processing and control. Volume 48(2019)
• Page Start: 128
• Page End: 143
• Publication Date: 2019-02
• Subjects: Robust automatic voice condition analysis -- Universal background models -- Extralinguistic aspects of the speech -- Cross-dataset validation; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2018.09.003
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: This is the second of a two-part series devoted to the automatic voice condition analysis of voice pathologies, being a direct continuation to the paper On the design of automatic voice condition analysis systems. Part I: review of concepts and an insight to the state of the art . The aim of this study is to examine several variability factors affecting the robustness of systems that automatically detect the presence of voice pathologies by means of audio registers. Multiple experiments are performed to test out the influence of the speech task, extralinguistic aspects (such as sex), the acoustic features and the classifiers in their performance. Some experiments are carried out using state-of-the-art classification methodologies often employed in speaker recognition. In order to evaluate the robustness of the methods, testing is repeated across several corpora with the aim to create a single system integrating the conclusions obtained previously. This system is later tested under cross-dataset scenarios in an attempt to obtain more realistic conclusions. Results identify a reduced subset of relevant features, which are used in a hierarchical-like scenario incorporating information of different speech tasks. In particular, for the experiments carried out using the Saarbrüecken voice dataset, the area under the ROC curve of the system reached 0.88 in an intra-dataset setting and ranged from 0.82 to 0.94 in cross-dataset scenarios. These results let us open a discussion about the suitability of these techniques to be transferred to the clinical setting.