Acoustic modeling method based on gated recurrent unit

A technology of recurrent units and modeling methods, applied in neural learning methods, biological neural network models, speech analysis, etc., can solve problems such as limiting speech recognition system performance, insufficient noise data robustness, long training time, etc., to improve recognition Performance, improved convergence speed, and improved robustness

Inactive Publication Date: 2020-11-13
成都启英泰伦科技有限公司
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, in practical applications, this type of method is still far from the requirements of large-scale commercialization. The reason is that GRU still has problems such as too many model parameters, too long training time, and not robust enough to noisy data. Greatly limit the performance of speech recognition systems

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Acoustic modeling method based on gated recurrent unit
  • Acoustic modeling method based on gated recurrent unit
  • Acoustic modeling method based on gated recurrent unit

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Specific embodiments of the present invention will be further described in detail below.

[0024] The acoustic modeling method based on the gated recurrent unit of the present invention can be used in the scene of continuous speech recognition, and can also be used in modeling under other situations related to speech recognition, specifically as figure 1 shown.

[0025] Step 1. Extract the corresponding acoustic features from the original audio data , the subscript t=1, 2, ..., T, where T is the frame number of the speech signal.

[0026] Step 2. Use layer normalization to improve the gated recurrent unit, use the improved gated recurrent unit function to calculate the forward output of the neural network, and normalize it to obtain the output probability of each neuron;

[0027] Regularization can use the softmax function;

[0028] The specific way of normalization is:

[0029] (1.0)

[0030] in, yes Corresponding No. elements, The network output label...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an acoustic modeling method based on a gated recurrent unit. The acoustic modeling method comprises the following steps: step 1, extracting corresponding acoustic features fromoriginal audio data; step 2, improving the gated recurrent unit by utilizing layer normalization, and calculating forward output of a neural network by utilizing the improved gated recurrent unit; step 3, training a model according to the state vector, calculated in the step 2, of the current moment; and step 4, decoding the trained model to find an output sequence with the maximum probability. According to the invention, the layer normalization technology is applied to the gated recurrent neural unit, so that the activation value of neurons can be normalized, the network convergence speed isimproved, and the network training time is reduced; an activation function in a traditional gated recurrent unit is replaced with an ELU activation function, so that the data robustness is improved;meanwhile, by optimizing a computational formula of the gate structure, model parameters of a traditional gated recurrent unit are reduced, and the recognition performance of the model can be improved.

Description

technical field [0001] The invention belongs to the technical field of speech recognition and relates to an acoustic modeling method, in particular to an acoustic modeling method based on a gated recurrent unit. Background technique [0002] In recent years, with the continuous development of artificial intelligence and computer technology, deep learning technology has been widely used in image, voice and other fields. As one of the most natural interaction interfaces between machines and humans, speech has become a research hotspot in academia and industry. [0003] The acoustic model is one of the core modules of the speech recognition system, and its performance directly affects the entire speech system. Before 2009, the basic structure of the acoustic model was a Gaussian Mixture Model-Hidden Markov Model (GMM-HMM). However, with the successful application of neural networks in the field of speech recognition, the traditional GMM- HMM is gradually replaced by DNN-HMM (...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/06G10L15/14G10L15/16G06N3/08
CPCG06N3/084G10L15/063G10L15/144G10L15/148G10L15/16G10L2015/0631
Inventor 温登峰何云鹏许兵
Owner 成都启英泰伦科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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