Processing affected speech within human machine interaction. Magdeburg: Otto-von-Guericke Universitat

Spoken dialog systems (SDS) integrated into human-machine interaction interfaces is becoming a standard technology. Cur-rent state-of-the-art SDS, usually, is not able to provide for the user a natural way of communication. Existing automated dia-log systems do not dedicate enough attention to problems in the interaction related to affected user behavior. As a result, Auto-matic Speech Recognition (ASR) engines are not able to recog-nize affected speech and dialog strategy does not make use of the user’s emotional state. This paper addresses some aspects of processing affected speech within natural human-machine inter-action. First of all, we propose an affected speech adapted ASR engine. Second, we describe our methods of emotion recog-nition within speech and present our results of emotion clas-sification within Interspeech 2009 Emotion Challenge. Third, we test affected speech adapted speech recognition models and introduce an approach to achieve emotion adaptive dialog man-agement in human-machine interaction