People and animals fuse auditory and visual information to obtain robust perception. A particular benefit of such cross-modal analysis is the ability to localize visual events associated with sound sources. We aim to achieve this using computer-vision aided by a single microphone. Past efforts encountered problems stemming from the huge gap between the dimensions involved and the available data. This has led to solutions suffering from low spatio-temporal resolutions. We present a rigorous analysis of the fundamental problems associated with this task. Then, we present a stable and robust algorithm which overcomes past deficiencies. It grasps dynamic audio-visual events with high spatial resolution, and derives a unique solution. The algorithm effectively detects pixels that are associated with the sound, while filtering out other dynamic pixels. It is based on canonical correlation analysis (CCA), where we remove inherent ill-posedness by exploiting the typical spatial sparsity of audio-visual events. The algorithm is simple and efficient thanks to its reliance on linear programming and is free of user-defined parameters. To quantitatively assess the performance, we devise a localization criterion. The algorithm capabilities were demonstrated in experiments, where it overcame substantial visual distractions and audio noise. 1

This paper presents a novel method to correlate audio and visual data generated by the same physical phenomenon, based on sparse geometric representation of video sequences. The video signal is modeled as a sum of geometric primitives evolving through time, that jointly describe the geometric and motion content of the scene. The displacement through time of relevant visual features, like the mouth of a speaker, can thus be compared with the evolution of an audio feature to assess the correspondence between acoustic and visual signals. Experiments show that the proposed approach allows to detect and track the speaker’s mouth when several persons are present on the scene, in presence of distracting motion, and without prior face or mouth detection.

In this work we explore the potentialities of a framework for the representation of audio-visual signals using decompositions on overcomplete dictionaries. Redundant decompositions may describe audio-visual sequences in a concise fashion, preserving good representation properties thanks to the use of redundant, well designed, dictionaries. We expect that this will help us overcome two typical problems of multimodal fusion algorithms. On one hand, classical representation techniques, like pixel-based measures (for the video) or Fourier-like transforms (for the audio), take into account only marginally the physics of the problem. On the other hand, the input signals have large dimensionality. The results we obtain by making use of sparse decompositions of audio-visual signals over redundant codebooks are encouraging and show the potentialities of the proposed approach to multimodal signal representation.

Abstract—In the context of the automated surveillance field, automatic scene analysis and understanding systems typically consider only visual information, whereas other modalities, such as audio, are typically disregarded. This paper presents a new method able to integrate audio and visual information for scene analysis in a typical surveillance scenario, using only one camera and one monaural microphone. Visual information is analyzed by a standard visual background/foreground (BG/FG) modelling module, enhanced with a novelty detection stage and coupled with an audio BG/FG modelling scheme. These processes permit one to detect separate audio and visual patterns representing unusual unimodal events in a scene. The integration of audio and visual data is subsequently performed by exploiting the concept of synchrony between such events. The audio-visual (AV) association is carried out on-line and without need for training sequences, and is actually based on the computation of a characteristic feature called audio-video concurrence matrix, allowing one to detect and segment AV events, as well as to discriminate between them. Experimental tests involving classification and clustering of events show all the potentialities of the proposed approach, also in comparison with the results obtained by employing the single modalities and without considering the synchrony issue. Index Terms—Audio-visual analysis, automated surveillance, event classification and clustering, multimodal background modelling and foreground detection, multimodality, scene analysis. I.

Abstract—We investigate a solution to the problem of multisensor scene understanding by formulating it in the framework of Bayesian model selection and structure inference. Humans robustly associate multimodal data as appropriate, but previous modeling work has focused largely on optimal fusion, leaving segregation unaccounted for and unexploited by machine perception systems. We illustrate a unifying Bayesian solution to multisensory perception and tracking, which accounts for both integration and segregation by explicit probabilistic reasoning about data association in a temporal context. Such an explicit inference of multimodal data association is also of intrinsic interest for higher level understanding of multisensory data. We illustrate this by using a probabilistic implementation of data association in a multiparty audiovisual scenario, where unsupervised learning and structure inference is used to automatically segment, associate, and track individual subjects in audiovisual sequences. Indeed, the structure-inference-based framework introduced in this work provides the theoretical foundation needed to satisfactorily explain many confounding results in human psychophysics experiments involving multimodal cue integration and association.

Abstract — It is well-known that early integration (also called data fusion) is effective when the modalities are correlated, and late integration (also called decision or opinion fusion) is optimal when modalities are uncorrelated. In this paper, we propose a new multimodal fusion strategy for open-set speaker identification using a combination of early and late integration following canonical correlation analysis (CCA) of speech and lip texture features. We also propose a method for high precision synchronization of the speech and lip features using CCA prior to the proposed fusion. Experimental results show that i) the proposed fusion strategy yields the best equal error rates (EER), which are used to quantify the performance of the fusion strategy for open-set speaker identification, and ii) precise synchronization prior to fusion improves the EER; hence, the best EER is obtained when the proposed synchronization scheme is employed together with the proposed fusion strategy. We note that the proposed fusion strategy outperforms others because the features used in the late integration are truly uncorrelated, since they are output of the CCA analysis. I.

Abstract not found

We present a method that exploits the information theoretic framework described in [1] to extract optimal audio features with respect to the video features. A simple measure of mutual information between the resulting audio features and the video ones allows to detect the active speaker among different candidates. The results show that our method is able to exploit the shared speech information contained in audio and video signals to recover their common source. 1.

Abstract—A method that exploits an information theoretic framework to extract optimized audio features using video information is presented. A simple measure of mutual information (MI) between the resulting audio and video features allows the detection of the active speaker among different candidates. This method involves the optimization of an MI-based objective function. No approximation is needed to solve this optimization problem, neither for the estimation of the probability density functions (pdfs) of the features, nor for the cost function itself. The pdfs are estimated from the samples using a nonparametric approach. The challenging optimization problem is solved using a global method: the differential evolution algorithm. Two information theoretic optimization criteria are compared and their ability to extract audio features specific to speech production is discussed. Using these specific audio features, candidate video features are then classified as member of the “speaker ” or “non-speaker” class, resulting in a speaker detection scheme. As a result, our method achieves a speaker detection rate of 100 % on in-house test sequences, and of 85 % on most commonly used sequences. Index Terms—Audio features, differential evolution, multimodal, mutual information, speaker detection, speech. I.

Abstract — For many practical probability density representations such as for the widely used Gaussian mixture densities, an analytic evaluation of the differential entropy is not possible and thus, approximate calculations are inevitable. For this purpose, the first contribution of this paper deals with a novel entropy approximation method for Gaussian mixture random vectors, which is based on a component-wise Taylor-series expansion of the logarithm of a Gaussian mixture and on a splitting method of Gaussian mixture components. The employed order of the Taylor-series expansion and the number of components used for splitting allows balancing between accuracy and computational demand. The second contribution is the determination of meaningful and efficiently to calculate lower and upper bounds of the entropy, which can be also used for approximation purposes. In addition, a refinement method for the more important upper bound is proposed in order to approach the true entropy value. I.