Towards efficient human machine speech communication

Abstract

This research investigates the design and performance of the Speech Graffiti interface for spoken interaction with simple machines. Speech Graffiti is a standardized interface designed to address issues inherent in the current state-of-the-art in spoken dialog systems such as high word-error rates and the difficulty of developing natural language systems. This article describes the general characteristics of Speech Graffiti, provides examples of its use, and describes other aspects of the system such as the development toolkit. We also present results from a user study comparing Speech Graffiti with a natural language dialog system. These results show that users rated Speech Graffiti significantly better in several assessment categories. Participants completed approximately the same number of tasks with both systems, and although Speech Graffiti users often took more turns to complete tasks than natural language interface users, they completed tasks in slightly less time.

Selecting Help Messages by Using Robust Grammar Verification for Handling Out-of-Grammar Utterances in Spoken Dialogue Systems

“…One way to prevent such errors is to acquaint users with the limitations of the system through a preceding tutorial session [9]. Tomko et al [10] designed a standardized protocol called "Speech Graffiti". They designed a subset language used in spoken dialogue systems and taught the user how to use it in a short tutorial session.…”

Flying Cities: building a 3D world from vocal input

“…(p. 36). Typically, speech interfaces in the Speech Graffiti project (Tomko et al 2005) or the VoiceCode system (Désilets et al 2006) rely on a database to establish an interview-style dialogue between the user(s) and the machine.…”

A study of out-of-turn interaction in menu-based, IVR, voicemail systems

“…Arons [2] studied interacting with an ATS decision tree through speech input (front, bottom-left corner of Fig. 4) and Tomko et al [14] studied the area between the (menu-based, voice-response, in-turn) and (natural language, voice-response, in-turn) points in the Speech Graffiti project. To the best of our knowledge, no study has explored the area between the (menu-based, voiceresponse, out-of-turn) and (menu-based, voice-response, inturn) points and, therefore, we contribute a study which does.…”