Iterative Large-Scale Pronunciation Dictionary Construction Method and Device

A construction method and large-scale technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of limited model scale, large manpower and material resources, etc., and achieve the effect of rapid and effective construction

Active Publication Date: 2021-05-25
数据堂(北京)科技股份有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Limited by the scale of the model, for the task of constructing a large-scale pronunciation dictionary, manually collecting and constructing the entries and phonetic symbols of the pronunciation dictionary requires a lot of manpower and material resources, so that the final pronunciation dictionary generally only has tens of thousands of entries about

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
  • Iterative Large-Scale Pronunciation Dictionary Construction Method and Device
  • Iterative Large-Scale Pronunciation Dictionary Construction Method and Device
  • Iterative Large-Scale Pronunciation Dictionary Construction Method and Device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments and descriptions of the present invention are used to explain the present invention, but not to limit the present invention.

[0029] Explanation of professional terms:

[0030] Speech recognition: refers to converting the vocabulary content in human speech into computer-readable input, such as binary codes, character sequences, etc., making the human-computer interface more natural and easy to use;

[0031] Iterative: refers to the way of training the model, which is a cyclical process, constantly using constraints to restrict the training of the model to optimize in a predetermined direction;

[0032] Pronunciation dictionary: refers to the dictionary in the speech recognition system, whic...

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 a method and device for constructing an iterative large-scale pronunciation dictionary, wherein the method includes: generating a sequence of entries according to raw text data; generating a sequence of phonetic symbols according to raw data of audio; generating a binary sequence using a G2P model according to the sequence of entries. Group <词条，音标>; According to the sequence of phonetic symbols, use the P2G model to generate a pair <音标，词条>;Calculate the matching degree between two pairs, and compare it with the preset matching degree, and compare the pairing degree corresponding to the matching degree less than the preset matching degree <词条，音标>and dyads <音标，词条>Extract discriminative samples to obtain discriminative samples; obtain the labeling and correction of discriminative samples by domain experts, and convert the labeled and corrected binary groups <词条，音标>and dyads <音标，词条>Stored in a multi-level large-scale pronunciation dictionary. The invention can quickly and effectively construct a large-scale pronunciation dictionary, improve the working efficiency of a speech recognition system and reduce labor costs.< / 音标，词条>

Description

technical field [0001] The invention relates to the technical field of dictionary construction, in particular to an iterative large-scale pronunciation dictionary construction method and device. Background technique [0002] This section is intended to provide a background or context to embodiments of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] With the continuous innovation of science and technology, the voice field has also developed rapidly, which has also driven the continuous update and iteration of the language recognition system. The speech recognition system consists of three parts, namely the acoustic model, the pronunciation dictionary and the language model. Among them, the pronunciation dictionary is a very important part of the speech recognition system, and it is a bridge connecting the acoustic model and the speech model. Therefore, for a speech recognition syst...

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 Patents(China)
IPC IPC(8): G10L15/06G10L15/16G10L15/02
CPCG10L15/02G10L15/063G10L15/16G10L2015/025G10L2015/0631G10L2015/0633
Inventor 王治愚王大亮王丽媛齐红威
Owner 数据堂(北京)科技股份有限公司
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