Voice identifying method based on deep neural network characteristic training

A deep neural network, speech recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of inaccurate speech recognition and high word error rate

Inactive Publication Date: 2017-07-04
SHENZHEN WEITESHI TECH
View PDF0 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, speech recognition still has the problem of

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
  • Voice identifying method based on deep neural network characteristic training
  • Voice identifying method based on deep neural network characteristic training
  • Voice identifying method based on deep neural network characteristic training

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0031] figure 1 It is a system frame diagram of a speech recognition method based on deep neural network feature training in the present invention. It mainly includes Gabor filter bank characteristics, Gabor filter subgroups, deep neural network (DNN) implementation and identification.

[0032] A deep neural network (DNN) implementation can be divided into two stages: pre-training and cross-entropy tuning; in the former stage, stacks of Restricted Boltzmann Machines (RBMs) are trained one layer at a time in a greedy fashion using contrastive divergence , also known as Deep Belief Network (DBN); in the latter stage, as the backbone of the final network, the DBN is fine-tuned to classif...

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 provides a voice identifying method based on deep neural network characteristic training. The method involves the realization and identification of Gabor filter bank characteristics, Gabor filter sub-banks, and a deep neural network (DNN), which is achieved through the following steps: a Gabor filter extracting automatic voice identifying characteristics from a voice signal, firstly on the basis of a distributive voice identification standard, extracting a logarithm Me 1 spectrogram from the voice signal, then conducting convolution on the spectrogram and each 2D filter from the Gabor filter bank; selecting a specific modulation frequency, such that a transfer function of the filter exhibits constant overlapping in a modulated frequency field; an automatic voice identifying system, on the basis of character error rate in a test set, carrying on evaluation, and finally acquiring an identification result. According to the invention, the Gabor filter sub-bank can reduce character and word identification errors, and exhibit the channel distortion resistance and low signal-to-noise ratio. The method uses a voice identifier having a high time modulation filter, has low error rate, and increases the distinctiveness among object types.

Description

technical field [0001] The invention relates to the field of speech recognition, in particular to a speech recognition method based on deep neural network feature training. Background technique [0002] Speech recognition takes speech as the research object and involves many fields such as physiology, psychology, linguistics, computer science, and signal processing. Its ultimate goal is to realize natural language communication between humans and machines, and to manipulate computers with language. In the past ten years, significant progress has been made in automatic speech recognition, and its application in our daily life has become more and more extensive. For example, some telephones and mobile phones have included voice recognition dialing functions, some voice Products such as smart toys also include speech recognition and speech synthesis functions. People can already use voice to inquire about information such as air tickets, travel, hotels, etc. through the teleph...

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
IPC IPC(8): G10L15/02G10L15/06G10L15/16G10L15/30G10L19/02G10L19/26G10L25/18G10L25/30
CPCG10L15/02G10L15/063G10L15/16G10L15/30G10L19/02G10L19/26G10L25/18G10L25/30
Inventor 夏春秋
Owner SHENZHEN WEITESHI TECH
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