Voice recognition method and system

A technology for speech recognition and to-be-recognized, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of large memory usage, long time consumption, and reduced speech recognition efficiency, so as to reduce the demand for product memory, easy to implement, The effect of improving the scope of application and recognition efficiency

Active Publication Date: 2018-08-17
AISPEECH CO LTD
View PDF14 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the inventors of the present application found that the technical solutions in the above-mentioned related technologies have at least the following defects in the process of practicing the present application: in the first strategy, because the preset dictionary table cannot be applied to the neural network, and WFST also It is not a neural network, so it needs to store a large amount of language model information and occupy a large amount of memory. It is generally implemented by deploying WFST in the cloud, and its sear

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 recognition method and system
  • Voice recognition method and system
  • Voice recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0020] In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0021] It should be noted that the embodiments in the application and the features in the embodiments can be combined with each other if there is no conflict.

[0022] The invention can be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, program modules in...

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 voice recognition method and system. The voice recognition method comprises the steps of extracting the acoustic features of voice data to be recognized; decoding the acoustic features into a phoneme array based on the acoustic-phoneme neural network model; and further decoding the phoneme array into a text sequence based on phoneme-language neural network model. According to the voice recognition system provided by the embodiment of the invention, phoneme array output by the acoustic-phoneme neural network model can be used as the input of a phoneme-language neural network model, which seamlessly joins the acoustic-phoneme neural network model and the phoneme-language neural network model. Generally, a brand new end-to-end voice recognition framework is provided,and the voice recognition efficiency is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of voice analysis, in particular to a voice recognition method and system. Background technique [0002] Speech recognition enables machines to automatically convert speech into corresponding text through machine learning methods. It is widely used in various smart terminals, and it also makes more and more users accustomed to inputting words by voice. [0003] At present, there are roughly two strategies for speech recognition processing in related technologies: the first strategy is to decompose the speech data into different acoustic feature vectors, and use the WFST (weighted finaite-state transducer, weighted finite state transcription machine) The dictionary table, decoding the candidate words corresponding to the acoustic feature vector; the second strategy, the end-to-end speech recognition scheme based on the neural network, specifically inputting the acoustic features to the speech recognition mode...

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): G10L15/02G10L15/16G10L15/26
CPCG10L15/02G10L15/16G10L15/26G10L2015/025
Inventor 俞凯陈哲怀刘奇李豪游永彬
Owner AISPEECH CO LTD
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