Improving automatic detection of obstructive sleep apnea through nonlinear analysis of sustained speech

We present a novel approach for the detection of severe obstructive sleep apnea (OSA) based on patients' voices introducing nonlinear measures to describe sustained speech dynamics. Nonlinear features were combined with state-of-the-art speech recognition systems using statistical modeling techniques (Gaussian mixture models, GMMs) over cepstral parameterization (MFCC) for both continuous and sustained speech. Tests were performed on a database including speech records from both severe OSA and control speakers. A 10 % relative reduction in classification error was obtained for sustained speech when combining MFCC-GMM and nonlinear features, and 33 % when fusing nonlinear features with both sustained and continuous MFCC-GMM. Accuracy reached 88.5 % allowing the system to be used in OSA early detection. Tests showed that nonlinear features and MFCCs are lightly correlated on sustained speech, but uncorrelated on continuous speech. Results also suggest the existence of nonlinear effects in OSA patients' voices, which should be found in continuous speech.

Towards an Asynchronous Cinema: how can the asynchronous use of sound in artists' moving image underpin the creation of dialectic tension between the audio, the visual and the audience?

This PhD by publication examines selected practice-based audio-visual works made by the author over a ten-year period, placing them in a critical context. Central to the publications, and the focus of the thesis, is an exploration of the role of sound in the creation of dialectic tension between the audio, the visual and the audience. By first analysing a number of texts (films/videos and key writings) the thesis locates the principal issues and debates around the use of audio in artists’ moving image practice. From this it is argued that asynchronism, first advocated in 1929 by Pudovkin as a response to the advent of synchronised sound, can be used to articulate audio-visual relationships. Central to asynchronism’s application in this paper is a recognition of the propensity for sound and image to adhere, and in visual music for there to be a literal equation of audio with the visual, often married with a quest for the synaesthetic. These elements can either be used in an illusionist fashion, or employed as part of an anti-illusionist strategy for realising dialectic. Using this as a theoretical basis, the paper examines how the publications implement asynchronism, including digital mapping to facilitate innovative reciprocal sound and image combinations, and the asynchronous use of ‘found sound’ from a range of online sources to reframe the moving image. The synthesis of publications and practice demonstrates that asynchronism can both underpin the creation of dialectic, and be an integral component in an audio-visual anti-illusionist methodology.

Visual activity predicts auditory recovery from deafness after adult cochlear implantation.

Modern cochlear implantation technologies allow deaf patients to understand auditory speech; however, the implants deliver only a coarse auditory input and patients must use long-term adaptive processes to achieve coherent percepts. In adults with post-lingual deafness, the high progress of speech recovery is observed during the first year after cochlear implantation, but there is a large range of variability in the level of cochlear implant outcomes and the temporal evolution of recovery. It has been proposed that when profoundly deaf subjects receive a cochlear implant, the visual cross-modal reorganization of the brain is deleterious for auditory speech recovery. We tested this hypothesis in post-lingually deaf adults by analysing whether brain activity shortly after implantation correlated with the level of auditory recovery 6 months later. Based on brain activity induced by a speech-processing task, we found strong positive correlations in areas outside the auditory cortex. The highest positive correlations were found in the occipital cortex involved in visual processing, as well as in the posterior-temporal cortex known for audio-visual integration. The other area, which positively correlated with auditory speech recovery, was localized in the left inferior frontal area known for speech processing. Our results demonstrate that the visual modality's functional level is related to the proficiency level of auditory recovery. Based on the positive correlation of visual activity with auditory speech recovery, we suggest that visual modality may facilitate the perception of the word's auditory counterpart in communicative situations. The link demonstrated between visual activity and auditory speech perception indicates that visuoauditory synergy is crucial for cross-modal plasticity and fostering speech-comprehension recovery in adult cochlear-implanted deaf patients.

The development of an automatic recognition system for earmark and earprint comparisons

The value of earmarks as an efficient means of personal identification is still subject to debate. It has been argued that the field is lacking a firm systematic and structured data basis to help practitioners to form their conclusions. Typically, there is a paucity of research guiding as to the selectivity of the features used in the comparison process between an earmark and reference earprints taken from an individual. This study proposes a system for the automatic comparison of earprints and earmarks, operating without any manual extraction of key-points or manual annotations. For each donor, a model is created using multiple reference prints, hence capturing the donor within source variability. For each comparison between a mark and a model, images are automatically aligned and a proximity score, based on a normalized 2D correlation coefficient, is calculated. Appropriate use of this score allows deriving a likelihood ratio that can be explored under known state of affairs (both in cases where it is known that the mark has been left by the donor that gave the model and conversely in cases when it is established that the mark originates from a different source). To assess the system performance, a first dataset containing 1229 donors elaborated during the FearID research project was used. Based on these data, for mark-to-print comparisons, the system performed with an equal error rate (EER) of 2.3% and about 88% of marks are found in the first 3 positions of a hitlist. When performing print-to-print transactions, results show an equal error rate of 0.5%. The system was then tested using real-case data obtained from police forces.

L'effort associé à la reconnaissance de la parole chez les adultes et les personnes aînées

L’objectif principal de cette thèse était de quantifier et comparer l’effort requis pour reconnaître la parole dans le bruit chez les jeunes adultes et les personnes aînées ayant une audition normale et une acuité visuelle normale (avec ou sans lentille de correction de la vue). L’effort associé à la perception de la parole est lié aux ressources attentionnelles et cognitives requises pour comprendre la parole. La première étude (Expérience 1) avait pour but d’évaluer l’effort associé à la reconnaissance auditive de la parole (entendre un locuteur), tandis que la deuxième étude (Expérience 2) avait comme but d’évaluer l’effort associé à la reconnaissance auditivo-visuelle de la parole (entendre et voir le visage d’un locuteur). L’effort fut mesuré de deux façons différentes. D’abord par une approche comportementale faisant appel à un paradigme expérimental nommé double tâche. Il s’agissait d’une tâche de reconnaissance de mot jumelée à une tâche de reconnaissance de patrons vibro-tactiles. De plus, l’effort fut quantifié à l’aide d’un questionnaire demandant aux participants de coter l’effort associé aux tâches comportementales. Les deux mesures d’effort furent utilisées dans deux conditions expérimentales différentes : 1) niveau équivalent – c'est-à-dire lorsque le niveau du bruit masquant la parole était le même pour tous les participants et, 2) performance équivalente – c'est-à-dire lorsque le niveau du bruit fut ajusté afin que les performances à la tâche de reconnaissance de mots soient identiques pour les deux groupes de participant. Les niveaux de performance obtenus pour la tâche vibro-tactile ont révélé que les personnes aînées fournissent plus d’effort que les jeunes adultes pour les deux conditions expérimentales, et ce, quelle que soit la modalité perceptuelle dans laquelle les stimuli de la parole sont présentés (c.-à.-d., auditive seulement ou auditivo-visuelle). Globalement, le ‘coût’ associé aux performances de la tâche vibro-tactile était au plus élevé pour les personnes aînées lorsque la parole était présentée en modalité auditivo-visuelle. Alors que les indices visuels peuvent améliorer la reconnaissance auditivo-visuelle de la parole, nos résultats suggèrent qu’ils peuvent aussi créer une charge additionnelle sur les ressources utilisées pour traiter l’information. Cette charge additionnelle a des conséquences néfastes sur les performances aux tâches de reconnaissance de mots et de patrons vibro-tactiles lorsque celles-ci sont effectuées sous des conditions de double tâche. Conformément aux études antérieures, les coefficients de corrélations effectuées à partir des données de l’Expérience 1 et de l’Expérience 2 soutiennent la notion que les mesures comportementales de double tâche et les réponses aux questionnaires évaluent différentes dimensions de l’effort associé à la reconnaissance de la parole. Comme l’effort associé à la perception de la parole repose sur des facteurs auditifs et cognitifs, une troisième étude fut complétée afin d’explorer si la mémoire auditive de travail contribue à expliquer la variance dans les données portant sur l’effort associé à la perception de la parole. De plus, ces analyses ont permis de comparer les patrons de réponses obtenues pour ces deux facteurs après des jeunes adultes et des personnes aînées. Pour les jeunes adultes, les résultats d’une analyse de régression séquentielle ont démontré qu’une mesure de la capacité auditive (taille de l’empan) était reliée à l’effort, tandis qu’une mesure du traitement auditif (rappel alphabétique) était reliée à la précision avec laquelle les mots étaient reconnus lorsqu’ils étaient présentés sous les conditions de double tâche. Cependant, ces mêmes relations n’étaient pas présentes dans les données obtenues pour le groupe de personnes aînées ni dans les données obtenues lorsque les tâches de reconnaissance de la parole étaient effectuées en modalité auditivo-visuelle. D’autres études sont nécessaires pour identifier les facteurs cognitifs qui sous-tendent l’effort associé à la perception de la parole, et ce, particulièrement chez les personnes aînées.

Modeling High-Dimensional Audio Sequences with Recurrent Neural Networks

Cette thèse étudie des modèles de séquences de haute dimension basés sur des réseaux de neurones récurrents (RNN) et leur application à la musique et à la parole. Bien qu'en principe les RNN puissent représenter les dépendances à long terme et la dynamique temporelle complexe propres aux séquences d'intérêt comme la vidéo, l'audio et la langue naturelle, ceux-ci n'ont pas été utilisés à leur plein potentiel depuis leur introduction par Rumelhart et al. (1986a) en raison de la difficulté de les entraîner efficacement par descente de gradient. Récemment, l'application fructueuse de l'optimisation Hessian-free et d'autres techniques d'entraînement avancées ont entraîné la recrudescence de leur utilisation dans plusieurs systèmes de l'état de l'art. Le travail de cette thèse prend part à ce développement. L'idée centrale consiste à exploiter la flexibilité des RNN pour apprendre une description probabiliste de séquences de symboles, c'est-à-dire une information de haut niveau associée aux signaux observés, qui en retour pourra servir d'à priori pour améliorer la précision de la recherche d'information. Par exemple, en modélisant l'évolution de groupes de notes dans la musique polyphonique, d'accords dans une progression harmonique, de phonèmes dans un énoncé oral ou encore de sources individuelles dans un mélange audio, nous pouvons améliorer significativement les méthodes de transcription polyphonique, de reconnaissance d'accords, de reconnaissance de la parole et de séparation de sources audio respectivement. L'application pratique de nos modèles à ces tâches est détaillée dans les quatre derniers articles présentés dans cette thèse. Dans le premier article, nous remplaçons la couche de sortie d'un RNN par des machines de Boltzmann restreintes conditionnelles pour décrire des distributions de sortie multimodales beaucoup plus riches. Dans le deuxième article, nous évaluons et proposons des méthodes avancées pour entraîner les RNN. Dans les quatre derniers articles, nous examinons différentes façons de combiner nos modèles symboliques à des réseaux profonds et à la factorisation matricielle non-négative, notamment par des produits d'experts, des architectures entrée/sortie et des cadres génératifs généralisant les modèles de Markov cachés. Nous proposons et analysons également des méthodes d'inférence efficaces pour ces modèles, telles la recherche vorace chronologique, la recherche en faisceau à haute dimension, la recherche en faisceau élagué et la descente de gradient. Finalement, nous abordons les questions de l'étiquette biaisée, du maître imposant, du lissage temporel, de la régularisation et du pré-entraînement.

Perceptual Evaluation of Video-Realistic Speech

abstract With many visual speech animation techniques now available, there is a clear need for systematic perceptual evaluation schemes. We describe here our scheme and its application to a new video-realistic (potentially indistinguishable from real recorded video) visual-speech animation system, called Mary 101. Two types of experiments were performed: a) distinguishing visually between real and synthetic image- sequences of the same utterances, ("Turing tests") and b) gauging visual speech recognition by comparing lip-reading performance of the real and synthetic image-sequences of the same utterances ("Intelligibility tests"). Subjects that were presented randomly with either real or synthetic image-sequences could not tell the synthetic from the real sequences above chance level. The same subjects when asked to lip-read the utterances from the same image-sequences recognized speech from real image-sequences significantly better than from synthetic ones. However, performance for both, real and synthetic, were at levels suggested in the literature on lip-reading. We conclude from the two experiments that the animation of Mary 101 is adequate for providing a percept of a talking head. However, additional effort is required to improve the animation for lip-reading purposes like rehabilitation and language learning. In addition, these two tasks could be considered as explicit and implicit perceptual discrimination tasks. In the explicit task (a), each stimulus is classified directly as a synthetic or real image-sequence by detecting a possible difference between the synthetic and the real image-sequences. The implicit perceptual discrimination task (b) consists of a comparison between visual recognition of speech of real and synthetic image-sequences. Our results suggest that implicit perceptual discrimination is a more sensitive method for discrimination between synthetic and real image-sequences than explicit perceptual discrimination.

Robust and fast vowel recognition using optimum-path forest

The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.

Contextos comunicacionais adequados e inadequados à inclusão de alunos com deficiência visual em aulas de mecânica

This article is inserted in a study aimed at the identification of the main barriers for the inclusion of visually-impaired students in Physics classes. It focuses on the understanding of the communication context which facilitates or hardens the effective participation of students with visual impairment in Mechanics activities. To do so, the research defines, from empirical - sensory and semantic structures, the language to be applied in the activities, as well as, the moment and the speech pattern in which the languages have been used. As a result, it identifies the rela tion between the uses of the interdependent audio-visual empirical lan guage structure in the non-interactive episodes of authority; the decrease in the use of this structure in interactive episodes; the creation of educa tional segregation environments within the classroom and the frequent use of the interdependent tactile-hearing empirical language structure in such environments.

Contextos comunicacionais adequados e inadequados à inclusão de alunos com deficiência visual em aulas de termologia

This article represents a continuation of the results of a research presented in Camargo and Nardi (2007). It is inserted in the study that seeks to understand the main student’s inclusion barriers with visual impairment in the Physics classes. It aims to understand which communication context shows kindness or unkindness to the impairment visual student’s real participation in thermology activities. For this, the research defines, from the empirical - sensory and semantics structures, the used languages in the activities, as well, the moment and the speech pattern in which the languages have been used. As result, identifies a strong relation between the uses of the interdependent empirical structure audio-visual language in the non-interactive episodes of authority; a decrease of this structure use in the interactive episodes and the creation of education segregation environments within the classroom.

Contextos comunicacionales adecuados e inadecuados para la inclusión de alumnos con discapacidad visual en clases de física moderna

This article is inserted in a wider study that seeks to understand the main inclusion barriers in Physics classes for students with visual impairment It aims to understand which communication context favors or impedes the visually impaired student participation to the impairment visual student’s real participation in Modern Physics activities. The research defines, from the empirical-sensory and semantics structures, the languages used in the activities, as well as, the moment and the speech pattern in which those languages have been used. As a result, this study identifies a strong relation between the uses of the interdependent empirical structure audio-visual language in the non-interactive episodes of authority; a decrease of this structure use in the interactive episodes; the creation of education segregation environments within the clasroom and the frequent use of empirical tactile-hearing interdependent language structure in these environments. Moreover, the concept of «special educational need» is discussed and its inadequate use is analyzed. Suggestions are given for its correct use of «special educational need,» its inadequate use, giving suggestions for its correct use.

Neural basis of visual deficits recovery: visual residual functions and multisensory integration.

The ability of integrating into a unified percept sensory inputs deriving from different sensory modalities, but related to the same external event, is called multisensory integration and might represent an efficient mechanism of sensory compensation when a sensory modality is damaged by a cortical lesion. This hypothesis has been discussed in the present dissertation. Experiment 1 explored the role of superior colliculus (SC) in multisensory integration, testing patients with collicular lesions, patients with subcortical lesions not involving the SC and healthy control subjects in a multisensory task. The results revealed that patients with collicular lesions, paralleling the evidence of animal studies, demonstrated a loss of multisensory enhancement, in contrast with control subjects, providing the first lesional evidence in humans of the essential role of SC in mediating audio-visual integration. Experiment 2 investigated the role of cortex in mediating multisensory integrative effects, inducing virtual lesions by inhibitory theta-burst stimulation on temporo-parietal cortex, occipital cortex and posterior parietal cortex, demonstrating that only temporo-parietal cortex was causally involved in modulating the integration of audio-visual stimuli at the same spatial location. Given the involvement of the retino-colliculo-extrastriate pathway in mediating audio-visual integration, the functional sparing of this circuit in hemianopic patients is extremely relevant in the perspective of a multisensory-based approach to the recovery of unisensory defects. Experiment 3 demonstrated the spared functional activity of this circuit in a group of hemianopic patients, revealing the presence of implicit recognition of the fearful content of unseen visual stimuli (i.e. affective blindsight), an ability mediated by the retino-colliculo-extrastriate pathway and its connections with amygdala. Finally, Experiment 4 provided evidence that a systematic audio-visual stimulation is effective in inducing long-lasting clinical improvements in patients with visual field defect and revealed that the activity of the spared retino-colliculo-extrastriate pathway is responsible of the observed clinical amelioration, as suggested by the greater improvement observed in patients with cortical lesions limited to the occipital cortex, compared to patients with lesions extending to other cortical areas, found in tasks high demanding in terms of spatial orienting. Overall, the present results indicated that multisensory integration is mediated by the retino-colliculo-extrastriate pathway and that a systematic audio-visual stimulation, activating this spared neural circuit, is able to affect orientation towards the blind field in hemianopic patients and, therefore, might constitute an effective and innovative approach for the rehabilitation of unisensory visual impairments.

Residual visual processing following real or virtual lesions to primary visual pathways

Lesions to the primary geniculo-striate visual pathway cause blindness in the contralesional visual field. Nevertheless, previous studies have suggested that patients with visual field defects may still be able to implicitly process the affective valence of unseen emotional stimuli (affective blindsight) through alternative visual pathways bypassing the striate cortex. These alternative pathways may also allow exploitation of multisensory (audio-visual) integration mechanisms, such that auditory stimulation can enhance visual detection of stimuli which would otherwise be undetected when presented alone (crossmodal blindsight). The present dissertation investigated implicit emotional processing and multisensory integration when conscious visual processing is prevented by real or virtual lesions to the geniculo-striate pathway, in order to further clarify both the nature of these residual processes and the functional aspects of the underlying neural pathways. The present experimental evidence demonstrates that alternative subcortical visual pathways allow implicit processing of the emotional content of facial expressions in the absence of cortical processing. However, this residual ability is limited to fearful expressions. This finding suggests the existence of a subcortical system specialised in detecting danger signals based on coarse visual cues, therefore allowing the early recruitment of flight-or-fight behavioural responses even before conscious and detailed recognition of potential threats can take place. Moreover, the present dissertation extends the knowledge about crossmodal blindsight phenomena by showing that, unlike with visual detection, sound cannot crossmodally enhance visual orientation discrimination in the absence of functional striate cortex. This finding demonstrates, on the one hand, that the striate cortex plays a causative role in crossmodally enhancing visual orientation sensitivity and, on the other hand, that subcortical visual pathways bypassing the striate cortex, despite affording audio-visual integration processes leading to the improvement of simple visual abilities such as detection, cannot mediate multisensory enhancement of more complex visual functions, such as orientation discrimination.

Content Classification of Multimedia Documents using Partitions of Low-Level Features

Audio-visual documents obtained from German TV news are classified according to the IPTC topic categorization scheme. To this end usual text classification techniques are adapted to speech, video, and non-speech audio. For each of the three modalities word analogues are generated: sequences of syllables for speech, “video words” based on low level color features (color moments, color correlogram and color wavelet), and “audio words” based on low-level spectral features (spectral envelope and spectral flatness) for non-speech audio. Such audio and video words provide a means to represent the different modalities in a uniform way. The frequencies of the word analogues represent audio-visual documents: the standard bag-of-words approach. Support vector machines are used for supervised classification in a 1 vs. n setting. Classification based on speech outperforms all other single modalities. Combining speech with non-speech audio improves classification. Classification is further improved by supplementing speech and non-speech audio with video words. Optimal F-scores range between 62% and 94% corresponding to 50% - 84% above chance. The optimal combination of modalities depends on the category to be recognized. The construction of audio and video words from low-level features provide a good basis for the integration of speech, non-speech audio and video.

Internet video telephony allows speech reading by deaf individuals and improves speech perception by cochlear implant users

OBJECTIVE To analyze speech reading through Internet video calls by profoundly hearing-impaired individuals and cochlear implant (CI) users. METHODS Speech reading skills of 14 deaf adults and 21 CI users were assessed using the Hochmair Schulz Moser (HSM) sentence test. We presented video simulations using different video resolutions (1280 × 720, 640 × 480, 320 × 240, 160 × 120 px), frame rates (30, 20, 10, 7, 5 frames per second (fps)), speech velocities (three different speakers), webcameras (Logitech Pro9000, C600 and C500) and image/sound delays (0-500 ms). All video simulations were presented with and without sound and in two screen sizes. Additionally, scores for live Skype™ video connection and live face-to-face communication were assessed. RESULTS Higher frame rate (>7 fps), higher camera resolution (>640 × 480 px) and shorter picture/sound delay (<100 ms) were associated with increased speech perception scores. Scores were strongly dependent on the speaker but were not influenced by physical properties of the camera optics or the full screen mode. There is a significant median gain of +8.5%pts (p = 0.009) in speech perception for all 21 CI-users if visual cues are additionally shown. CI users with poor open set speech perception scores (n = 11) showed the greatest benefit under combined audio-visual presentation (median speech perception +11.8%pts, p = 0.032). CONCLUSION Webcameras have the potential to improve telecommunication of hearing-impaired individuals.