No abstract

This paper presents a low-complexity variable step-size control for acoustic echo cancellation filters. The proposed control method is based on two supplementary adaptive filters with low memory length. The first supplementary filter is used to control the double-talk situations while the second supplementary filter is employed to detect variations of the echo-path impulse response. The variable step-size here derived is independent from the echo coupling loss and from the reverberation time and thus it is suitable for both hands-free and handset terminals

No abstract

No abstract

This paper describes a rule-based fuzzy system that estimates the relationship between acoustic and visual speech and uses this estimate for the synchronization of not aligned audio-visual signals. The relations are quantified by means of a set of rules, which associate typical mouth shapes (visual classes) t o specific acoustic classes. The visual and acoustic classes are learned from training data using automatic clustering algorithms, relying on the clustering tendency of the extracted feature vectors and without performing phonetic recognition. Nevertheless, the categorical fuzzy structure of the system allows to recognize, with some degree of uncertainty, the phonetic and visematic characteristics of the speech signal, making thus possible the integration of other sources of information in a human-like way.