Mathematical foundations of speech and language processing. (Q1880574): Difference between revisions
From MaRDI portal
Set profile property. |
Set OpenAlex properties. |
||
Property / full work available at URL | |||
Property / full work available at URL: https://doi.org/10.1007/978-1-4419-9017-4 / rank | |||
Normal rank | |||
Property / OpenAlex ID | |||
Property / OpenAlex ID: W335758531 / rank | |||
Normal rank |
Latest revision as of 20:05, 19 March 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Mathematical foundations of speech and language processing. |
scientific article |
Statements
Mathematical foundations of speech and language processing. (English)
0 references
29 September 2004
0 references
The importance of language text and speech technologies continues to grow since these techniques are used to transcribe, analyze, route and extract written and spoken information, competing to create natural and efficient interfaces between people and machines. This book is a collection of 12 high-quality contributions selected from the papers of two workshops organized by IMA (Institute of Mathematics and its Applications), University of Minnesota, September and November 2000, and dedicated to the mathematical foundations of speech and natural language text processing. The twelve original contributions emphasize the role of mathematics, statistics, logic, formal languages and parsing to the understanding of complex phenomena in speech and natural language, as well as to filling the gap between practitioners and mathematicians when facing the concrete problems of text and speech processing. The first four papers (chapters) of the book contain expositions related to language processing, moving from more general work to specific advances in structure and topic representations in language modelling. The fifth paper deals with prosody modelling, and provides a nice transition towards speech since prosody may be seen as an important link between phonetics and global language structure. The next five papers relate primarily to acoustic modelling, starting with work that is motivated by speech production models and acoustic-phonetic studies, and moving toward new and more general models. The book concludes with two papers from the statistics community that are addressed to speech and language processing in the future. For a closer look, here there are the authors and titles of the contained papers: Chapter 1. Stuart Geman, Mark Johnson: Probability and statistics in computational linguistics, a brief review; Chapter 2. Dietrich Klakow: Three issues in modern language modeling; Chapter 3. Frederik Jelinek: Stochastic analysis of structured language modeling; Chapter 4. Jerome R. Bellegarda: Latent semantic language modeling for speech recognition; Chapter 5. Elizabeth Shriberg, Andreas Stolcke: Prosody modeling for automatic speech recognition and understanding; Chapter 6. Li Deng: Switching dynamic system models for speech articulation and acoustics; Chapter 7. Wendy J. Holmes: Segmental HMMS: Modeling dynamics and underlying structure in speech; Chapter 8. James R. Glass: Modelling graph-based observation spaces for segment-based speech recognition; Chapter 9. Herve Bourland, Samy Bengio, Katrin Weber: Towards robust and adaptive speech recognition models; Chapter 10. Jeffrey A. Bilmes: Graphical models and automatic speech recognition; Chapter 11. Julian Besag: An introduction to Markov chain Monte Carlo methods; Chapter 12. Benjamin Kedem, Konstantinos Fokianos: Semiparametric filtering in speech processing.
0 references
natural language technology
0 references
computational linguistics
0 references
speech processing
0 references
prosody modelling
0 references
text programming
0 references
stochastic approach to language processing
0 references