Gestures During Overlapping Speech in multimodal Human−Machine Dialogues
نویسندگان
چکیده
A dialogue system has to deal with the problem of interruptions by the user, e.g. changes of requests (called »barge−in«). This contribution is concerned with this problem in the special case of the multimodal dialogue system SmartKom. How are gestures used during such interruptions if they are utilized at all? To answer this question we analyzed a number of human− machine dialogues qualitatively. The analysis showed that most overlap situations were not accompanied by gestures at all. In the remaining instances the gestures were almost never "interactional" gestures, but mostly "unidentifiable" and "emotional" ones. We allocated the overlap situations accompanied by gestures to several subcategories of barge−in, pointed out the peculiarities of the gestures in the different cases and discussed their suitability as indicators for the dialogue system. Although from a small−scale in depth analysis no generalizations can be drawn, valuable insights for further investigation have been won. Most importantly it can be noted that the dynamic features of gestures seem far more promising as indicators of dialogue situations that need to be taken care of by the dialogue system than their static features. 1.1
منابع مشابه
What and Where: An Empirical Investigation of Pointing Gestures and Descriptions in Multimodal Referring Actions
Pointing gestures are pervasive in human referring actions, and are often combined with spoken descriptions. Combining gesture and speech naturally to refer to objects is an essential task in multimodal NLG systems. However, the way gesture and speech should be combined in a referring act remains an open question. In particular, it is not clear whether, in planning a pointing gesture in conjunc...
متن کاملTowards generation of fluent referring action in a multimodal situations
We have been developing a system that uses natural language in combination with visual information such as pictures and gestures, to generate effective explanations. The experimental system we implemented is for explaining the installation and operation of a telephone with answering machine feature, and simulates instruction dialogues performed by an expert in a face-to-face situation with a te...
متن کاملA Corpus of Natural Multimodal Spatial Scene Descriptions
We present a corpus of multimodal spatial descriptions, as commonly occurring in route giving tasks. Participants provided natural spatial scene descriptions with speech and abstract deictic/iconic hand gestures. The scenes were composed of simple geometric objects. While the language denotes object shape and visual properties (e.g., colour), the abstract deictic gestures “placed” objects in ge...
متن کاملPossible Lexical Indicators for Barge−In / Barge−Before in a multimodal Man− Machine−Communication
Even in inter−human dialogues there are situations where it is not clear whether the speaker will continue with his/her speech or whether the dialogue partner wants to take the next turn. Of course, regarding multimodal dialogues, we not only have speech for input and output but also gestural input or graphical output. In this paper we concentrate on the linguistic analysis of the user’s lingui...
متن کاملIntonation vs. Gestures in Yes-No Answers
Yes-No answers have traditionally posed major difficulties in speech recognition: the amount of signal is too short and may lead to mis-recognition. We think that the speech signal itself, that is, intonation (F0 and energy) are not enough to fulfil this task. When the information the signal can provide is so little, we must look for other sources. This paper analyzes intonation and gestures to...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001