Ute Winter

Cultural Analyses of In-car Communication

What if new cars could adjust in-car devices to particular ways of speaking around the world? General Motors sought communication research to inform the design of culturally competent in-car human–machine interfaces. We discuss concerns and tensions that arise when balancing commitments of naturalistic study with design development goals. We emphasize the importance of awareness, attentiveness, and cooperation to ensure research integrity.

Language pattern analysis for automotive natural language speech applications

Natural language speech user interfaces offer a compelling choice of user interaction for the automotive market. With the increasing number of domains in which speech applications are applied, drivers must currently memorize many command words to control traditional speech interfaces. In contrast, natural language interfaces demand only a basic understanding of the system model instead of memorizing keywords and predefined patterns. To utilize natural language interfaces optimally, designers need to better comprehend how people utter their requests to express their intentions. In this study, we collected a corpus of utterances from users who interacted freely with an automotive natural language speech application. We analyzed the corpus by employing a corpus linguistic technique. As a result, natural language utterances can be classified into three components: information data, context relevant words, and non context relevant vocabulary. Applying this classification, users tended to repeat similar utterance patterns composed from a very limited set of different words. Most of the vocabulary in longer utterances was found to be non context restrictive providing no information. Moreover, users could be distinguished by their language patterns. Finally, this information can be used for the development of natural language speech applications. Some initial ideas are discussed in the paper.

Design of Multimodal Mobile Interfaces

The book discusses the new world of mobile multimodality, focusing on innovative technologies and design which create a state-of-the-art user interface. It examines the practical challenges entailed in meeting commercial deployment goals, and offers new approaches to designing such interfaces.

Cross Cultural Comparison of Users' Barge-in with the In-Vehicle Speech System

The focus of this paper is user barge-in behavior during interactions with an in-vehicle speech system. This study is part of a cross-cultural research conducted in the US and China that explored the cultural differences regarding users’ expectations and interactions with in-vehicle speech applications. In this paper, we describe the methodology of the field study, the interface of the prototype, the experimental set up, the analysis procedure, as well as the participants’ demographics from both the US and China. We categorize the observed barge-in behavior and the typical scenarios in which it occurred, from both prompt timing and a dialog sequence perspective. After analyzing all barge-in instances, we discuss design implications for a barge-in feature and system prompts of an in-vehicle speech system that considers the different cultural norms of the two regions.

A model for investigating cultural dimensions of communication in the car

ABSTRACT This article explicates a theoretical framework which was designed to discover cultural features both within and about car communication. The general approach the framework provides has been used for basic research in the United States and China, and has proven useful to researchers and designers. We discuss specifically how the approach can develop and implement speech-enabled human–machine interface (HMI) systems to address cultural features of communication and interaction. The general framework unveils the cultural nature of human–machine communication, while it also opens the possibility of discovering new cultural dimensions and principles which designers may not yet have considered. The approach is adaptable to a variety of communication contexts, with our focus here on the in-car communication of drivers with a speech-enabled HMI. Specific findings are briefly discussed including implications for research and design.