E ective Speaker Tracking Strategies for Multi-party Human-Computer Dialogue

Human-computer dialogue is already a rather mature research eld [10] that already stemmed to several commercial applications, either service or taskoriented [11]. Nevertheless, several issues remain to be tackled, when unrestricted, spontaneous dialogue is concerned: barge-in (when users interrupt the system or interrupt each other) must be properly handled, hence Voice Activity Detection is a crucial point [13]. Moreover, when multi-party interactions are allowed (i.e., the machine engages simultaneously in dialogue with several users), supplementary robustness constraints occur: the speakers have to be properly tracked, so that each utterance is mapped to a certain speaker that had produced it. This is needed in order to perform a reliable analysis of input utterances [2]. Spoken human-computer dialogue systems can be seen as advanced applications of spoken language technology. A dialogue system represents a voiced and relatively natural interface between the user and a software application. Thus, spoken dialogue systems subsume most of the elds in spoken language technology, including speech recognition and synthesis, natural language processing, and dialogue management (planning). A dialogue system involves the integration of several components, which generally provide the following functions [3]: