𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Speech understanding systems

✍ Scribed by A. Newell; J. Barnett; J.W. Forgie; C. Green; D. Klatt; J.C.R. Licklider; J. Munson; D.R. Reddy; W.A. Woods


Publisher
Elsevier Science
Year
1972
Tongue
English
Weight
73 KB
Volume
3
Category
Article
ISSN
0004-3702

No coin nor oath required. For personal study only.

✦ Synopsis


This report is being published under the aegis of the journa! Artificial Intelligence. The journal will, from time to time, publish as special issues reports, monographs, surveys, etc., which for some good reason---e.g, sizeuare not appropriate for incorporation in its regular runs. This is the first such.

It is substantially the report prepared by a group of distinguished American computer scientists, under the chairmanship of Professor Allen Neweli, for the Advanced Research Projects Agency (A.R.P.A.) of the U.S. Department of Defense. Some minor editorial changes have been made, to make it more suitable for an international scientific readership. It is so important a document, addressed to one of the most difficult and challenging issues of artificial intelligence, that it is really a public duty for the journal to make it far more easily available and accessible than it was in its original form as an A.R.P.A. report.

The study is correctly named as being of speech understanding rather than speech recognition, thu~ indicating its dedication to the central theme of current research in A.~. Although the study group has ceased to exist as ~uch, the report has been followed by a substantial research and development effort. This effort involves a high degree of continuing cooperation among all of the various participating resea~'ch groups. The field of artificial intelligence faces a genuine problem of how to organize to create large systems that are far too dependent on new research to be handled as pure development efforts, yet involve much of the paced and managed engineering approach appropriate to attaining well-defined complex technical goals. This experiment in cooperation adds to the purely scientific interest of the document.

The Editors of the journal are grateful to the Advanced Research Projects Agency for permission an(; co-operation in bringing out this issue.


πŸ“œ SIMILAR VOLUMES


Speech understanding systems
✍ A. Newell; J. Barnett; J.W. Forgie; C. Green; D. Klatt; J.C.R. Licklider; J. Mun πŸ“‚ Article πŸ“… 1973 πŸ› Elsevier Science 🌐 English βš– 65 KB

This report is being published under the aegis of the journal Artificial Intelligence. The journal will, from time to time, publish as special issues reports, monographs, surveys, etc., which for some good reason--e.g. ~ize--are not appropriate for incorporation in its regular runs. This is the firs

Language portability of a speech underst
✍ Mauro Cettolo; Anna Corazza; Renato De Mori πŸ“‚ Article πŸ“… 1998 πŸ› Elsevier Science 🌐 English βš– 305 KB

An important problem in automatic speech understanding is the transport of an existing application system to a new language. Design choices are required to keep the cost and implementation time of the porting as low as possible. One of the bottlenecks in spoken language system development is represe

Speech understanding systems: Report of
✍ M.F. Medress; F.S. Cooper; J.W. Forgie; C.C. Green; D.H. Klatt; M.H. O'Malley; E πŸ“‚ Article πŸ“… 1977 πŸ› Elsevier Science 🌐 English βš– 753 KB

A five-year interdisciplinary effort by speech scientists and computer scientists has demmtstrated the feasibility of programming a computer system to "understand" connected speech, i.e., translate it into operational form and respond accordingly. An operational system (HARP Y) accepts speech from f

Recognition confidence scoring and its u
✍ Timothy J. Hazen; Stephanie Seneff; Joseph Polifroni πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 145 KB

In this paper we present an approach to recognition confidence scoring and a set of techniques for integrating confidence scores into the understanding and dialogue components of a speech understanding system. The recognition component uses a multi-tiered approach where confidence scores are compute

Context-dependent probability adaptation
✍ Erwin W Drenth; Bernhard RΓΌber πŸ“‚ Article πŸ“… 1997 πŸ› Elsevier Science 🌐 English βš– 331 KB

By using context-dependent concept language models, we can significantly improve the performance of the speech understanding component of a dialogue system. We use several different modelling methods, such as bigrams, concept set probability estimations using graph theory and combinations of these.

Understanding complex systems
✍ Manfred Gilli; Edouard Rossier πŸ“‚ Article πŸ“… 1981 πŸ› Elsevier Science 🌐 English βš– 409 KB