End-to-end speech recognition method based on adaptive learning rate
An adaptive learning rate, speech recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as complex speech recognition framework, and achieve the effect of simplifying the process and reducing the impact
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0034] The present invention will be further described in detail below in conjunction with the drawings.
[0035] Such as figure 2 As shown, the present invention provides an end-to-end speech recognition method based on an adaptive learning rate; the method specifically includes:
[0036] (1) Using a two-way recurrent neural network as the acoustic model to calculate the forward and backward hidden layers of the recurrent neural network, namely with The specific process is as follows:
[0037] Suppose the input feature sequence uses x=(x 1 ,..., x T ), then the forward recurrent neural network hidden layer It can be described by formula (1);
[0038]
[0039] Among them, σ is the sigmoid activation function, Is the weight matrix connecting the input layer and the hidden layer, Is the weight matrix connecting the output of the hidden layer at t-1 and the hidden layer at time t, Is the bias, x t Represents the input at time t, Represents the output of the hidden layer at t-1, R...
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