Recent spoken dialog systems are moving away from command and control towards a more intuitive and natural style of interaction. In order to choose an appropriate system design which allows the system to deal with naturally spoken user input, a definition of what exactly constitutes naturalness in user input is important. In this paper, we examine how different user groups naturally speak to an automotive spoken dialog system (SDS). We conduct a user study in which we collect freely spoken user utterances for a wide range of use cases in German. By means of a comparative study of the utterances from the study with interpersonal utterances, we provide criteria what constitutes naturalness in the user input of an state-of-the-art automotive SDS.

Recent spoken dialog systems have been able to recognize freely spoken user input in restricted domains thanks to statistical methods in the automatic speech recognition. These methods require a high number of natural language utterances to train the speech recognition engine and to assess the quality of the system. Since human speech offers many variants associated with a single intent, a high number of user utterances have to be elicited. Developers are therefore turning to crowdsourcing to collect this data. This paper compares three different methods to elicit multiple utterances for given semantics via crowd sourcing, namely with pictures, with text and with semantic entities. Specifically, we compare the methods with regard to the number of valid data and linguistic variance, whereby a quantitative and qualitative approach is proposed. In our study, the method with text led to a high variance in the utterances and a relatively low rate of invalid data.