Natural spoken dialogue systems for telephony applications

The article focuses on cognitive modeling for games and animation Biblioteca de Ciencias y Tecnología Normal Biblioteca de Ciencias y Tecnología 2 109 2006-05-26T00: 20: 00Z 2006-05-26T00: 20: 00Z 1 165 909 UCLA 7 2 1072 11. 6568 Clean Clean 21 false false false MicrosoftInternetExplorer4 /* Style Definitions */ table. MsoNormalTable mso-style-name: "Tabla normal"; mso-tstyle-rowband-size: 0; mso-tstyle-colband-size: 0; mso-style-noshow: yes; mso-style-parent: ""; mso-padding-alt: 0cm 5. 4pt 0cm 5. 4pt; mso-para-margin: 0cm; mso-para-margin-bottom: . 0001pt; mso-pagination: widow-orphan; font-size: 10. 0pt; font-family: "Times New Roman"; mso-ansi-language: #0400; mso-fareast-language: #0400; mso-bidi-language: #0400; Natural-language speech recognition refers to computer systems that recognize and act on unconstrained speech. Using this technology, the user does not need to know a predefined set of command words in order to use the system successfully. The article discusses the application of this technology for telephony applications. Limited to current technology, natural spoken-language systems are likely to respond to fluently spoken dialogue only if it falls within their specialized task domains. Spoken dialogue systems have several compelling advantages over the interactive voice response system generally used in telephony. Callers can state their requests in their own language and do not have to listen to a list of commands; and the hierarchical design of the interface is flattened to become more user friendly. The article discusses the operation of AT&T Corp. 's "Spoken Dialogue System, " which employs the speech recognition technology. A primary argument against these systems is they create unrealistic user expectations, leading to disappointment with the system.