Isolation word identification method based on double-layer GMM structure and VTS feature compensation
A recognition method and technology of isolated words, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of long recognition time of the isolated word recognition system, and achieve the effect of reducing time, overall time and estimation time.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0043] Such as figure 1 As shown, in the model training stage, two GMM models are trained by using the pure speech training data of all isolated words, in which the Gaussian unit mixture number of GMM1 is 10, the Gaussian unit mixture number of GMM2 is 100, and the mixture number of the HMM model is 4 The number of states is 6. The GMM model represents the distribution of characteristic parameters of all isolated words in a pure environment, and the HMM model represents the distribution of characteristic parameters of each isolated word in a pure environment.
[0044]In the recognition stage based on feature compensation, based on the vector Taylor series VTS feature compensation algorithm, according to the GMM1 model obtained in the training stage, the mean value and variance of the noise in the test speech in the test environment are estimated by the maximum likelihood probability criterion ML; then based on the minimum The mean square error estimation criterion MMSE and GM...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com