Cross-language end-to-end speech recognition method for low resource Tujia language

A technology of speech recognition and speech recognition model, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as low resources, and achieve the effect of improved recognition rate and significant recognition rate

Inactive Publication Date: 2018-12-14
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
View PDF5 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings of the above-mentioned prior art, the present invention discloses a cross-language end-to-end speech recognition me

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
  • Cross-language end-to-end speech recognition method for low resource Tujia language
  • Cross-language end-to-end speech recognition method for low resource Tujia language
  • Cross-language end-to-end speech recognition method for low resource Tujia language

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings.

[0033] The present invention utilizes the method of multilingual (Multi-lingual) speech recognition and transfer learning (Transfer Learning), and the specific implementation process is as follows figure 1 As shown, model A is a model obtained by using Tujia language corpus as training data, model B is a model obtained by using Tujia language and Chinese corpus as training data, and model C continues to use Tujia language on the basis of initial model Model B The corpus is used as the training data to get the model.

[0034]During specific implementation, the present invention adopts 2 layers of convolutional neural networks (Convolutional Neural Network, CNN), 3 layers of bidirectional long-short-term memory networks (Bi-directional Long Short-Term Memory, BiLSTM) and connection timing classification (Connectionist Temporal Classification, CTC) combined end-to-end sp...

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 cross-language end-to-end speech recognition method for the low resource Tujia language. The method comprises the following steps: preprocessing the Tujia language data; constructing a cross-language Tujia language corpus; establishing a unified coding dictionary of Chinese international phonetic alphabets and national international phonetic alphabets; establishing a cross-language end-to-end Tujia speech recognition model; and using a join temporal classification model and performing decoding under the action of the coding dictionary so as to obtain the recognition result. The recognition model with higher generalization is constructed by taking advantage of sufficient major language data and combining the idea of transfer learning so as to improve the accuracy of Tujia language speech recognition.

Description

technical field [0001] The invention belongs to the field of speech recognition and relates to a cross-language end-to-end speech recognition method for low-resource Tujia languages. Background technique [0002] With the development of Internet technology and the improvement of computer computing power and hardware, speech recognition technology has once again ushered in a new upsurge, especially in recent years, deep learning has once again ignited the enthusiasm of scientists for speech recognition technology. Speech recognition technology has a wide range of applications. With the development of artificial intelligence, speech recognition technology not only includes functions such as voice dialing, voice navigation, voice document retrieval, simple dictation data entry, etc., but also includes intelligent traffic control, indoor equipment control, etc. , smart city and other applications. If the speech recognition technology can be well developed, it is believed that i...

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): G10L15/00G10L15/02G10L15/06G10L15/16G10L15/187
CPCG10L15/005G10L15/02G10L15/063G10L15/16G10L15/187G10L2015/025
Inventor 于重重陈运兵徐世璇刘畅
Owner BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
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