Abstract
This paper introduces the session "Technology in the Year 2001" and is the first of four papers dealing with the future of human-machine communication by voice. In looking to the future it is important to recognize both the difficulties of technological forecasting and the frailties of the technology as it exists today--frailties that are manifestations of our limited scientific understanding of human cognition. The technology to realize truly advanced applications does not yet exist and cannot be supported by our presently incomplete science of speech. To achieve this long-term goal, the authors advocate a fundamental research program using a cybernetic approach substantially different from more conventional synthetic approaches. In a cybernetic approach, feedback control systems will allow a machine to adapt to a linguistically rich environment using reinforcement learning.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Atal B. S. Speech technology in 2001: new research directions. Proc Natl Acad Sci U S A. 1995 Oct 24;92(22):10046–10051. doi: 10.1073/pnas.92.22.10046. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Furui S. Toward the ultimate synthesis/recognition system. Proc Natl Acad Sci U S A. 1995 Oct 24;92(22):10040–10045. doi: 10.1073/pnas.92.22.10040. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Levinson S. E. Speech recognition technology: a critique. Proc Natl Acad Sci U S A. 1995 Oct 24;92(22):9953–9955. doi: 10.1073/pnas.92.22.9953. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Marcus M. New trends in natural language processing: statistical natural language processing. Proc Natl Acad Sci U S A. 1995 Oct 24;92(22):10052–10059. doi: 10.1073/pnas.92.22.10052. [DOI] [PMC free article] [PubMed] [Google Scholar]