Jacques Koreman

Nonintrusive multibiometrics on a mobile device: a comparison of fusion techniques

In this article we test a number of score fusion methods for the purpose of multimodal biometric authentication. These tests were made for the SecurePhone project, whose aim is to develop a prototype mobile communication system enabling biometrically authenticated users to deal legally binding m-contracts during a mobile phone call on a PDA. The three biometrics of voice, face and signature were selected because they are all traditional non-intrusive and easy to use means of authentication which can readily be captured on a PDA. By combining multiple biometrics of relatively low security it may be possible to obtain a combined level of security which is at least as high as that provided by a PIN or handwritten signature, traditionally used for user authentication. As the relative success of different fusion methods depends on the database used and tests made, the database we used was recorded on a suitable PDA (the Qtek2020) and the test protocol was designed to reflect the intended application scenario, which is expected to use short text prompts. Not all of the fusion methods tested are original. They were selected for their suitability for implementation within the constraints imposed by the application. All of the methods tested are based on fusion of the match scores output by each modality. Though computationally simple, the methods tested have shown very promising results. All of the 4 fusion methods tested obtain a significant performance increase.

Correlates of Varying Vocal Fold Adduction Deficiencies in Perception and Production: Methodological and Practical Considerations

In this study the voice characteristics of normal male and female speakers are compared to those of two groups of patients with unilateral vocal fold paralysis. In order to enhance phonation, the patients in the first group compensate for the adduction deficiency which results from paralysis. The patients in the second group do not use compensatory strategies. Sustained vowels [i:, a:, u:] were produced by the speakers and scored for roughness, breathiness and hoarseness (RBH) by 8 raters. Although interrater agreement for RBH scores is only moderate on average, these percepts make consistent distinctions between the three speaker groups. Consistent but different distinctions are made between the three speaker groups for male and female speakers. The results show that male and female speakers should not be pooled in experimental studies of the pathological voice. Our results also indicate that female patients with a compensated unilateral vocal fold paralysis cannot be clinically evaluated solely on the basis of perception, because their voices cannot be distinguished from normal, healthy female speakers, despite their physiological impairment. The group distinctions made on the basis of RBH scores are supported by differences in the acoustic parameters which are derived by automatic analysis of the sustained vowels. Despite identical group distinctions for RBH scores and acoustic parameters, the acoustic basis of the percepts is not straightforward. Different acoustic predictors of the percepts were found for male compared to female speakers. Additionally, interrater differences point towards the presence of perceptual trading relations.

Frame Based Features

In this chapter we will discuss feature extraction methods for speaker classification. We introduce linear predictive coding, mel frequency cepstral coefficients and wavelets and perform experimental studies on AURORA and TIMIT data. For the speaker identification task, we can show that wavelets are beneficial.

Comparison of weighting strategies in early and late fusion approaches to audio-visual person authentication

Person authentication can be strongly enhanced by the combination of different modalities. This is also true for the face and voice signals, which can be obtained with minimal inconvenience for the user. However, features from each modality can be combined at various different levels of processing and for face and voice signals the advantage of fusion depends strongly on the way they are combined. The aim of the work presented is to investigate the optimal strategy for combining voice and face modalities for signals of varying quality. The experimental data are taken from a newly acquired database using a PDA, which contains audio-visual recordings in different conditions. Voice features use mel-frequency cepstral coefficients, while the face signal is parameterised using wavelet coefficients in certain subbands. Results are presented for both early (feature-level) and late (score-level) fusion. At each level different fixed and variable weightings are used, both to weight between frames within each modality and to weight between modalities, where weights are based on some measure of signal reliability, such as the accuracy of automatic face detection or the audio signal to noise ratio. In addition, the contribution to authentication of information from different areas of the face is explored to determine a regional weighting for the face coefficients.

Phonetic Knowledge in Speech Technology

The contributions to this volume are considered within the framework of the question: “What sort of phonetic knowledge is relevant to speech technology?” This discussion throws light on the existing and the potential relationship between speech technology and the phonetic sciences, the possibilities for mutual gain and the need, ultimately, for researchers to emerge who combine the interest and expertise needed in both areas.