Cristina Muñoz-Mulas

Characterizing Neurological Disease from Voice Quality Biomechanical Analysis

The dramatic impact of neurological degenerative pathologies in life quality is a growing concern nowadays. Many techniques have been designed for the detection, diagnosis, and monitoring of the neurological disease. Most of them are too expensive or complex for being used by primary attention medical services. On the other hand, it is well known that many neurological diseases leave a signature in voice and speech. Through the present paper, a new method to trace some neurological diseases at the level of phonation will be shown. In this way, the detection and grading of the neurological disease could be based on a simple voice test. This methodology is benefiting from the advances achieved during the last years in detecting and grading organic pathologies in phonation. The paper hypothesizes that some of the underlying neurological mechanisms affecting phonation produce observable correlates in vocal fold biomechanics and that these correlates behave differentially in neurological diseases than in organic pathologies. A general description about the main hypotheses involved and their validation by acoustic voice analysis based on biomechanical correlates of the neurological disease is given. The validation is carried out on a balanced database of normal and organic dysphonic patients of both genders. Selected study cases will be presented to illustrate the possibilities offered by this methodology.

Neuromorphic detection of speech dynamics

Speech and voice technologies are experiencing a profound review as new paradigms are sought to overcome some specific problems which cannot be completely solved by classical approaches. Neuromorphic Speech Processing is an emerging area in which research is turning the face to understand the natural neural processing of speech by the Human Auditory System in order to capture the basic mechanisms solving difficult tasks in an efficient way. In the present paper a further step ahead is presented in the approach to mimic basic neural speech processing by simple neuromorphic units standing on previous work to show how formant dynamics - and henceforth consonantal features - can be detected by using a general neuromorphic unit which can mimic the functionality of certain neurons found in the upper auditory pathways. Using these simple building blocks a General Speech Processing Architecture can be synthesized as a layered structure. Results from different simulation stages are provided as well as a discussion on implementation details. Conclusions and future work are oriented to describe the functionality to be covered in the next research steps.

Estimating Tremor in Vocal Fold Biomechanics for Neurological Disease Characterization

Neurological Diseases (ND) are affecting larger segments of aging population every year. Treatment is dependent on expensive accurate and frequent monitoring. It is well known that ND leave correlates in speech and phonation. The present work shows a method to detect alterations in vocal fold tension during phonation. These may appear either as hypertension or as cyclical tremor. Estimations of tremor may be produced by auto-regressive modeling of the vocal fold tension series in sustained phonation. The correlates obtained are a set of cyclicality coefficients, the frequency and the root mean square amplitude of the tremor. Statistical distributions of these correlates obtained from a set of male and female subjects are presented. Results from five study cases of female voice are also given.

Neurological disease detection and monitoring from voice production

The dramatic impact of neurological degenerative pathologies in life quality is a growing concern. It is well known that many neurological diseases leave a fingerprint in voice and speech production. Many techniques have been designed for the detection, diagnose and monitoring the neurological disease. Most of them are costly or difficult to extend to primary attention medical services. Through the present paper it will be shown how some neurological diseases can be traced at the level of phonation. The detection procedure would be based on a simple voice test. The availability of advanced tools and methodologies to monitor the organic pathology of voice would facilitate the implantation of these tests. The paper hypothesizes that some of the underlying mechanisms affecting the production of voice produce measurable correlates in vocal fold biomechanics. A general description of the methodological foundations for the voice analysis system which can estimate correlates to the neurological disease is shown. Some study cases will be presented to illustrate the possibilities of the methodology to monitor neurological diseases by voice.

KPCA vs. PCA study for an age classification of speakers

Kernel-PCA and PCA techniques are compared in the task of age and gender separation. A feature extraction process that discriminates between vocal tract and glottal source is implemented. The reason why speech is processed in that way is because vocal tract length and resonant characteristics are related to gender and age and there is also a great relationship between glottal source and age and gender. The obtained features are then processed with PCA and kernel-PCA techniques. The results show that gender and age separation is possible and that kernel-PCA (especially with RBF kernel) clearly outperforms classical PCA or no preprocessing features.

Wavelet description of the Glottal Gap

The Glottal Source correlates reconstructed from the phonated parts of voice may render interesting information with applicability in different fields. One of them is defective closure (gap) detection. Through the paper the background to explain the physical foundations of defective gap are reviewed. A possible method to estimate defective gap is also presented based on a Wavelet Description of the Glottal Source. The method is validated using results from the analysis of a gender-balanced speakers database. Normative values for the different parameters estimated are given. A set of study cases with deficient glottal closure is presented and discussed.

Detection of Speech Dynamics by Neuromorphic Units

Speech and voice technologies are experiencing a profound review as new paradigms are sought to overcome some specific problems which can not be completely solved by classical approaches. Neuromorphic Speech Processing is an emerging area in which research is turning the face to understand the natural neural processing of speech by the Human Auditory System in order to capture the basic mechanisms solving difficult tasks in an efficient way. In the present paper a further step ahead is presented in the approach to mimic basic neural speech processing by simple neuromorphic units standing on previous work to show how formant dynamics -and henceforth consonantal features-, can be detected by using a general neuromorphic unit which can mimic the functionality of certain neurons found in the Upper Auditory Pathways. Using these simple building blocks a General Speech Processing Architecture can be synthesized as a layered structure. Results from different simulation stages are provided as well as a discussion on implementation details. Conclusions and future work are oriented to describe the functionality to be covered in the next research steps.

Gender Detection in Running Speech from Glottal and Vocal Tract Correlates

Gender detection from running speech is a very important objective to improve efficiency in tasks as speech or speaker recognition, among others. Traditionally gender detection has been focused on fundamental frequency (f0) and cepstral features derived from voiced segments of speech. The methodology presented here discards f0 as a valid feature because its estimation is complicate, or even impossible in unvoiced fragments, and its relevance in emotional speech or in strongly prosodic speech is not reliable. The approach followed consists in obtaining uncorrelated glottal and vocal tract components which are parameterized as mel-frequency coefficients. K-fold and cross-validation using QDA and GMM classifiers showed detection rates as large as 99.77 in a gender-balanced database of running speech from 340 speakers.

Neuromorphic detection of vowel representation spaces

In this paper a layered architecture to spot and characterize vowel segments in running speech is presented. The detection process is based on neuromorphic principles, as is the use of Hebbian units in layers to implement lateral inhibition, band probability estimation and mutual exclusion. Results are presented showing how the association between the acoustic set of patterns and the phonologic set of symbols may be created. Possible applications of this methodology are to be found in speech event spotting, in the study of pathological voice and in speaker biometric characterization, among others.

New Method for Finding Optimum Number of Characteristics to Classify Speakers by Age

It is known that the amount of characteristics may be the bottleneck of a digital processing system. Finding a good method to detect which characteristics are the most important to identify a speaker would get better results with less characteristics. The classification of an adult speaker by their age is a big challenge since the adulthood is a long period without significant changes in voice. This study proposes a new method based on F-ratio, dispersion metric and also correlation between parameters to find a rank of features. A bootstrapping procedure determines the optimum number of characteristics within a feature vector to characterize a speaker. The results are compared with other non linear ranking methods. The proposed algorithm achieves a better performance in most cases.