Abstract
Computer speech synthesis has reached a high level of performance, with increasingly sophisticated models of linguistic structure, low error rates in text analysis, and high intelligibility in synthesis from phonemic input. Mass market applications are beginning to appear. However, the results are still not good enough for the ubiquitous application that such technology will eventually have. A number of alternative directions of current research aim at the ultimate goal of fully natural synthetic speech. One especially promising trend is the systematic optimization of large synthesis systems with respect to formal criteria of evaluation. Speech recognition has progressed rapidly in the past decade through such approaches, and it seems likely that their application in synthesis will produce similar improvements.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Allen J. Linguistic aspects of speech synthesis. Proc Natl Acad Sci U S A. 1995 Oct 24;92(22):9946–9952. doi: 10.1073/pnas.92.22.9946. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Carlson R. Models of speech synthesis. Proc Natl Acad Sci U S A. 1995 Oct 24;92(22):9932–9937. doi: 10.1073/pnas.92.22.9932. [DOI] [PMC free article] [PubMed] [Google Scholar]