Search and learning strategies for improving hidden Markov models
โ Scribed by Renato De Mori; Michael Galler; Fabio Brugnara
- Publisher
- Elsevier Science
- Year
- 1995
- Tongue
- English
- Weight
- 121 KB
- Volume
- 9
- Category
- Article
- ISSN
- 0885-2308
No coin nor oath required. For personal study only.
โฆ Synopsis
A speaker-independent automatic speech recognition system is developed using hidden Markov models (HMMs). Simulated annealing and randomized search are used to optimize discrete features of the system, including topologies, parameter ties, context clusters, and the sizes of mixture densities. Domain knowledge is used to initialize and to constrain the search, which optimizes recognition performance while reducing the number of model parameters. System performance results for new types of discrete and continuous HMMs measured on the TIMIT corpus are reported. The small set of context-independent phoneme HMMs produced is competitive with much larger systems of context-dependent models.
๐ SIMILAR VOLUMES
The binding of a major histocompatibility complex (MHC) molecule to a peptide originating in an antigen is essential to recognizing antigens in immune systems, and it has proved to be important to use computers to predict the peptides that will bind to an MHC molecule. The purpose of this paper is t
There are many proteins that share the same fold but have no clear sequence similarity. To predict the structure of these proteins, so called ''protein fold recognition methods'' have been developed. During the last few years, improvements of protein fold recognition methods have been achieved throu
## Abstract Protein phosphorylation, which is an important mechanism in posttranslational modification, affects essential cellular processes such as metabolism, cell signaling, differentiation, and membrane transportation. Proteins are phosphorylated by a variety of protein kinases. In this investi