Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

N-gram grammar model constructing method for voice identification and voice identification system

An n-gram grammar and speech recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of limited data volume, time-consuming and labor-intensive, etc., and achieve the effect of effective control, alleviation of sparsity, and optimization of the language model part.

Inactive Publication Date: 2016-01-20
INST OF ACOUSTICS CHINESE ACAD OF SCI +1
View PDF5 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the acquisition of manual annotations is time-consuming and laborious, so the amount of data is very limited. How to make full use of artificial annotation corpus has become the research goal of people.

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
  • N-gram grammar model constructing method for voice identification and voice identification system
  • N-gram grammar model constructing method for voice identification and voice identification system
  • N-gram grammar model constructing method for voice identification and voice identification system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The solution of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0029] The process flow of the n-gram grammar model construction method based on word vector expansion manual labeling process provided by the present invention is as follows figure 1 As shown, specifically include:

[0030] 1. Word vector training: The corresponding word vectors of the words in the dictionary are obtained through neural network language model training. The training adopts the classic NNLM form, and its structure diagram is as follows figure 2 shown.

[0031] The model consists of input layer, mapping layer, hidden layer and output layer. Each word in the dictionary is represented by a vector whose dimension is the size of the dictionary, with 1 in the position of the word and 0 in the remaining dimensions. For the n-gram model, the input layer input is a long vector composed of "n-1" word vectors connect...

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 an n-gram grammar model constructing method for voice identification and a voice identification system. The method comprises: step (101), training is carried out by using a neural network language model to obtain word vectors, and classification and multi-layer screening is carried out on word vectors to obtain parts of speech; step (102), manual marking is expanded by using a direct word frequency statistic method; and when same-kind-word substitution is carried out, direct statistics of 1-to-n-gram grammar combination units changing relative to an original sentence is carried out, thereby obtaining an n-gram grammar model of the expanding part; step (103), manual marking is carried out to generate a preliminary n-gram grammar model, model interpolation is carried out on the preliminary n-gram grammar model and the n-gram grammar model of the expanding part, thereby obtaining a final n-gram grammar model. In addition, the step (101) includes: step (101-1), inputting a mark and a training text; step (101-2), carrying out training by using a neural network language model to obtain corresponding work vectors of words in a dictionary; step (101-3), carrying out word vector classification by using a k mean value method; and step (101-4), carrying out multi-layer screening on the classification result to obtain parts of speech finally.

Description

technical field [0001] The present invention relates to a method for expanding artificially marked training corpus by using word vector classification in speech recognition to improve a language model, and specifically provides a method for constructing an n-gram grammar model for speech recognition and a speech recognition system. Background technique [0002] The currently used language model modeling technology is mainly n-gram language model (n-gramLanguageModel). This model has been widely used in the field of speech recognition because of its advantages of simple training, low complexity, and convenient use. However, the core idea of ​​the n-gram model is to model it through word frequency statistics. In areas where resources are scarce, such as the speech recognition system for telephone conversations (CTS), due to the limited size of the corpus, there are a large number of grammars that do not appear in the training corpus. Combination, we can only rely on the smoot...

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): G10L15/16G10L15/06
Inventor 张晴晴陈梦喆潘接林颜永红
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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