Method and system of speech recognition based on matching model secondary identification
A speech recognition and secondary recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of speech recognition accuracy drop and affect human-computer interaction experience, so as to ensure accuracy, improve user experience, and recognize accurately high degree of effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0027] Such as figure 1 As shown, the voice recognition method based on the secondary recognition of the matching model of the present invention includes the following steps:
[0028] (10) Voice processing: preprocessing and feature extraction of user input voice;
[0029] In the prior art, a common speech recognition model modeling process includes the following steps:
[0030] (1) Obtain a sufficient amount of marked training data, extract the Mel-domain cepstral coefficient (MFCC) of each training sample as an acoustic feature; organize the annotation information of the training data to extract the text feature vector
[0031] (2) Input the acoustic feature vector of the training sample into a deep neural network (DNN) composed of a restricted Boltzmann machine (RBM) stack, and use the GMM-HMM baseline system to obtain the output layer of the neural network through forced alignment. The network output results of the training samples are compared with the actual label information to...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap