Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

    Andreas Kellner

    This paper describes a conversational user interface to an Electronic Program Guide (EPG). It tries to mediate between the intricate functionality of devices on the one side and the user’s abstract intention on the other side. In contrast... more
    This paper describes a conversational user interface to an Electronic Program Guide (EPG). It tries to mediate between the intricate functionality of devices on the one side and the user’s abstract intention on the other side. In contrast to simple keyword-based voice command interfaces, conversational user interfaces allow the user to interact with services and devices without specific knowledge of keywords or menu structures by means of natural language input and co-operative dialogue. The SPICE prototype system described here combines a spoken dialogue interface with a touch-screen display to allow for natural and efficient multimodal interaction in various usage scenarios. This paper explains the underlying concepts of the SPICE multimodal conversational user interface and their realization in a prototype application Spoken Dialogue, Multimodal Interface, Conversational System
    This paper describes the SmartKom-Home system realized within the SmartKom project. It assists the user by means of a multi-modal dialogue system in the home environment. This involves the control of various devices and the access to... more
    This paper describes the SmartKom-Home system realized within the SmartKom project. It assists the user by means of a multi-modal dialogue system in the home environment. This involves the control of various devices and the access to services. SmartKom-Home is supposed to serve as a uniform interface to all these devices and services so the user is freed from the necessity to understand which of the devices to consult how and when to fulfill complex wishes. We describe the setting of this scenario together with the hardware used. We furthermore discuss the specific requirements that evolve in a home environment, and how they are handled in the project.
    Abstract: This paper describes a conversational user interface to an Electronic Program Guide (EPG). It tries to mediate between the intricate functionality of devices on the one side and the user’s abstract intention on the other side.... more
    Abstract: This paper describes a conversational user interface to an Electronic Program Guide (EPG). It tries to mediate between the intricate functionality of devices on the one side and the user’s abstract intention on the other side. In contrast to simple keyword-based voice command interfaces, conversational user interfaces allow the user to interact with services and devices without specific knowledge of keywords or menu structures by means of natural language input and co-operative dialogue. The SPICE prototype system described here combines a spoken dialogue interface with a touch-screen display to allow for natural and efficient multimodal interaction in various usage scenarios. This paper explains the underlying concepts of the SPICE multimodal conversational user interface and their realization in a prototype application
    The robust estimation of language models for new applications of spoken dialogue systems often suffers from a shortcoming of training material. An alternative to training a language model is to improve an initial language model using... more
    The robust estimation of language models for new applications of spoken dialogue systems often suffers from a shortcoming of training material. An alternative to training a language model is to improve an initial language model using material obtained while running the new system, thus adapting it to the new task. In this paper we investigate different methods for online- adaptation
    ... Uh, he is in the speech recognition group. Mike Anderson from the speech recognition group is currently in the terminal room G202. ... 5.1 Decision Rule In PADIS, the particular implementation of the prior-knowlegde term CG P(WIGS) is... more
    ... Uh, he is in the speech recognition group. Mike Anderson from the speech recognition group is currently in the terminal room G202. ... 5.1 Decision Rule In PADIS, the particular implementation of the prior-knowlegde term CG P(WIGS) is influenced by the following factors: ...
    SmartKom-Home demonstrates the use and benefit of an intelligent multimodal interface when controlling entertainment devices like a TV, a recorder, and a jukebox, and when accessing entertainment services like an electronic program guide... more
    SmartKom-Home demonstrates the use and benefit of an intelligent multimodal interface when controlling entertainment devices like a TV, a recorder, and a jukebox, and when accessing entertainment services like an electronic program guide combining speech and a handheld display with touch input. One important point is emphasizing the functional aspect, i.e., the user’s needs, conveyed to the system in a
    This paper describes the SmartKom-Home system realized within the SmartKom project. It assists the user by means of a multi-modal dialogue system in the home environment. This involves the control of various devices and the access to ser-... more
    This paper describes the SmartKom-Home system realized within the SmartKom project. It assists the user by means of a multi-modal dialogue system in the home environment. This involves the control of various devices and the access to ser- vices. SmartKom-Home is supposed to serve as a uniform in- terface to all these devices and services so the user is freed from the necessity to understand which of the devices to consult how and when to fulfill complex wishes. We describe the setting of this scenario together with the hardware used. We furthermore discuss the specific requirements that evolve in a home environ- ment, and how they are handled in the project.
    ... Starting from a spelled last name, the system asks for the spoken last name, first name, and street respectively and takes a combined decision on the joint probability over all dia-log turns [6]. The telephone database itself is used... more
    ... Starting from a spelled last name, the system asks for the spoken last name, first name, and street respectively and takes a combined decision on the joint probability over all dia-log turns [6]. The telephone database itself is used as additional knowledge source [5]. After a short ...