Spoken dialogue systems allow users to interact with computer-based applications such as databases and expert systems by using natural spoken language. The origins of spoken dialogue systems can be traced back to Artificial Intelligence research in the 1950s concerned with developing conversational interfaces. However, it is only within the last decade or so, with major advances in speech technology, that large-scale working systems have been developed and, in some cases, introduced into commercial environments. As a result many major telecommunications and software companies have become aware of the potential for spoken dialogue technology to provide solutions in newly developing areas such as computer-telephony integration. Voice portals, which provide a speech-based interface between a telephone user and Web-based services, are the most recent application of spoken dialogue technology. This article describes the main components of the technology---speech recognition, language understanding, dialogue management, communication with an external source such as a database, language generation, speech synthesis---and shows how these component technologies can be integrated into a spoken dialogue system. The article describes in detail the methods that have been adopted in some well-known dialogue systems, explores different system architectures, considers issues of specification, design, and evaluation, reviews some currently available dialogue development toolkits, and outlines prospects for future development.

/pdf/spoken-dialogue-technology-548u6qypik.pdf

Spoken Dialogue Technology

A popular approach to dialogue management is based on a finite state model, where user utterances trigger transitions between the dialogue states, and these states, in turn, determine the system's response. The paper describes an alternative dialogue planning algorithm based on the notion of filling in an electronic form, or "E-form". Each slot has associated prompts that guide the user through the dialogue, and a priority that determines the order in which the system tries to acquire information. These slots can be optional or mandatory. However, the user is not restricted to follow the system's lead, and is free to ignore the prompts and take the initiative in the dialogue. The E-form based dialogue planner has been used in an application to search a database of used car advertisements. The goal is to assist the user in selecting, from this database, a small list of cars which match their constraints. For a large number of dialogues collected from over 600 naive users, we found over 70% compliance in answering specific system prompts.

/pdf/a-form-based-dialogue-manager-for-spoken-language-3gnjrse90q.pdf

A form-based dialogue manager for spoken language applications

A dynamic voice user interface system is provided. The dynamic voice user interface system interacts with a user at a first level of formality. The voice user interface system then monitors history of user interaction and adjusts the voice user interface to interact with the user with a second level of formality based on the history of user interaction.

Dynamic interactive voice interface

Apparatus and method for recording data in a speech recognition system and recognizing spoken data corresponding to the recorded data. The apparatus and method responds to entered data by generating a string of phonetic transcriptions from the entered data. The data and generated phonetic transcription string associated therewith is recorded in a vocabulary lexicon of the speech recognition system. The apparatus and method responds to receipt of spoken data by constructing a model of subwords characteristic of the spoken data and compares the constructed subword model with ones of the recorded lexicon vocabulary recorded phonetic transcription strings to recognize the spoken data as the data identified by and associated with a phonetic transcription string matching the constructed subword string.

Automatic speech recognizer

This report provides an overview of the current issues and techniques for the modelling of dialogues using a computer. A dialogue management system can manage a dialogue between two or more agents, be they human or computer. Recently, increasingly complex dialogues are being modelled which allow a range of discourse phenomena including ellipsis and anaphoric reference. Such dialogues are thought to be similar to those between two humans, and accurate modelling of these phenomena leads to "pleasant", i.e. easy to talk to, and natural human-computer dialogues. Dialogue management can be classified into three often overlapping approaches: discourse grammars, plan-based and collaborative approaches. The design of a system often begins by eliciting the language used initially between two humans and later by Wizard of Oz experiments. Special issues relating to dialogue management systems are discussed including recovery strategies from different types of errors and the coding of dialogue in corpora. Lastly, approaches to evaluation are briefly discussed from the qualitative and quantitative viewpoints, recognising the importance and size of this sub-field.

Dialogue management systems: a survey and overview

A motor-operated handgun for making designs in carpet and the like and for forming cut pile fabrics by hand including mechanical latching arrangement for locking the yarn while the yarn is cut to produce a cut pile face and an adjustable yarn feed mechanism capable of being set to control the number of stitches per inch.

Anders Bækgaard

Papers

Rapid Prototyping of a Dialogue System Using a Generic Dialogue Development Platform

Experience with a dialogue description formalism for realistic applications

Spoken Language Dialogue Systems

The Danish Spoken Language Dialogue Project: a General Overview

Constructing a large size lexicon for a continuous speech recognition system.