Contact microphones, especially throat microphones, have been developed to be used in environments with high background noises to improve the speech intelligibility in communication. They pick up vibrations from the surface they are attached to and are therefore less sensitive to sound and noise from the air. Comparison of the speech intelligibility with other types of microphones have previously been done by letting test persons examine the communication devices in question. This study examines the possibility to make use of the STI-method instead and therefore make a comparison faster, more cost-efficient and customizable. The thought is that if the relationship between speech signals and vibrations were known, it could be used to transform the STI test signal to vibrations and then use the STImethod to estimate the speech intelligibility for the chosen contact microphone. This study, containing 22 men and women, evaluated the vibrations at the most suitable locations on the head for contact microphones and compared it with the speech signal of the same test person. Frequency responses were calculated for all locations of the head and a more detailed study showed that the frequency response of the neck may be approximated as a second order lowpass filter with a cut-off frequency of about 300 Hz that attenuates speech signals with higher frequencies. Experiments were also done to measure the STI value of a throat microphone with the known relationship. However, the results pointed out several problems that needs to be addressed before a STI method can be performed successfully. The results from this study may also be used to deeper study the relationships between different vibrations resulting from speech signals and suggestions on how the performance of contact microphones may be improved are given.

Dans ce travail, une approche de reconnaissance de l’orateur en utilisant un microphone de contact est développée et présentée. L'élément passif de contact est construit à partir d'un matériau piézoélectrique. La position du transducteur piézoélectrique sur le cou de l'individu peut affecter grandement la qualité du signal recueilli et par conséquent les informations qui en sont extraites. Ainsi, le milieu multicouche dans lequel les vibrations des cordes vocales se propagent avant d'être détectées par le transducteur est modélisé. Le meilleur emplacement sur le cou de l’individu pour attacher un élément transducteur particulier est déterminé en mettant en œuvre des techniques de simulation Monte Carlo et, par conséquent, les résultats de la simulation sont vérifiés en utilisant des expériences réelles. La reconnaissance est basée sur le signal généré par les vibrations des cordes vocales lorsqu'un individu parle et non sur le signal vocal à la sortie des lèvres qui est influencé par les résonances dans le conduit vocal. Par conséquent, en raison de la nature variable du signal recueilli, l'analyse a été effectuée en appliquant la technique de transformation de Fourier à court terme pour décomposer le signal en ses composantes de fréquence. Ces fréquences représentent les vibrations des cordes vocales (50-1000 Hz). Les caractéristiques en termes d'intervalle de fréquences sont extraites du spectrogramme résultant. Ensuite, un vecteur 1-D est formé à des fins d'identification. L'identification de l’orateur est effectuée en utilisant deux critères d'évaluation qui sont la mesure de la similarité de corrélation et l'analyse en composantes principales (ACP) en conjonction avec la distance euclidienne. Les résultats montrent qu'un pourcentage élevé de reconnaissance est atteint et que la performance est bien meilleure que de nombreuses techniques existantes dans la littérature. / In this work, a speaker recognition approach using a contact microphone is developed and presented. The contact passive element is constructed from a piezoelectric material. In this context, the position of the piezoelectric transducer on the individual’s neck may greatly affect the quality of the collected signal and consequently the information extracted from it. Thus, the multilayered medium in which the sound propagates before being detected by the transducer is modeled. The best location on the individual’ neck to place a particular transducer element is determined by implementing Monte Carlo simulation techniques and consequently, the simulation results are verified using real experiments. The recognition is based on the signal generated from the vocal cords’ vibrations when an individual is speaking and not on the vocal signal at the output of the lips that is influenced by the resonances in the vocal tract. Therefore, due to the varying nature of the collected signal, the analysis was performed by applying the Short Term Fourier Transform technique to decompose the signal into its frequency components. These frequencies represent the vocal folds’ vibrations (50-1000 Hz). The features in terms of frequencies’ interval are extracted from the resulting spectrogram. Then, a 1-D vector is formed for identification purposes. The identification of the speaker is performed using two evaluation criteria, namely, the correlation similarity measure and the Principal Component Analysis (PCA) in conjunction with the Euclidean distance. The results show that a high percentage of recognition is achieved and the performance is much better than many existing techniques in the literature.