Fusion of scores is a cornerstone of multimodal biometric systems composed of independent unimodal parts. In this work, we focus on quality-dependent fusion for speaker-face verification. To this end, we propose a universal model which can be trained for automatic quality assessment of both face and speaker modalities. This model estimates the quality of representations produced by unimodal systems which are then used to enhance the score-level fusion of speaker and face verification modules. We demonstrate the improvements brought by this quality-dependent fusion on the recent NIST SRE19 Audio-Visual Challenge dataset.

This paper follows the recent advances in speech recognition which recommend replacing the standard hybrid GMM/HMM approach by deep neural architectures. These models were shown to drastically improve recognition performances, due to their ability to capture the underlying structure of data. However, they remain particularly complex since the entire temporal context of a given phoneme is learned with a single model, which must therefore have a very large number of trainable weights. This work proposes an alternative solution that splits the temporal context into blocks, each learned with a separate deep model. We demonstrate that this approach significantly reduces the number of parameters compared to the classical deep learning procedure, and obtains better results on the TIMIT dataset, among the best of state-of-the-art (with a 20.20% PER). We also show that our approach is able to assimilate data of different nature, ranging from wide to narrow bandwidth signals.

This paper addresses the problem of unsupervised detection of recurrent audio segments in TV programs toward program structuring. Recurrent segments are the key elements in the process of program structuring. This allows a direct and non linear access to the main parts inside a program. It hence facilitates browsing within a recorded TV program or a program that is available on a TV-on-Demand service. Our work focuses on programs like entertainments, shows, magazines, news... It proposes an audio recurrence detection method. This is either applied over an episode or a set of episodes of the same program. Different types of audio descriptors are proposed and evaluated over an 65-hours video dataset corresponding to 112 episodes of TV programs.

No abstract

No abstract