Language-independent keyword retrieval method and system

A language-independent and keyword-independent technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as difficult to accurately estimate model parameters and affect system performance, so as to improve accuracy and improve retrieval effect Effect

Active Publication Date: 2017-01-18
IFLYTEK CO LTD
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the number of keyword training samples is limited, it is difficult to accurately estimate the model parameters under the MLE criterion, which affects the performance of the system.

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
  • Language-independent keyword retrieval method and system
  • Language-independent keyword retrieval method and system
  • Language-independent keyword retrieval method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0047] Generally speaking, the traditional keyword detection system based on the HMM / Filler framework adopts the keyword model based on MLE training, which is suitable for the situation where the training data is sufficient. Specifically, the system first uses the keyword sample data to train under the MLE criterion to obtain the HMM model of each keyword, and then uses all kinds of training data to obtain the Filler model. After receiving the audio file to be retrieved, the optimal path is searched from the search space constructed by the keyword model and the Filler model, and the location information of the keyword is determined. The keyword model construction process is as follows:

[0048] Step 1: Determin...

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 language-irrelevant keyword search method and system. The method comprises the steps of establishing a keyword model and an absorption model; optimizing the keyword model by training data; establishing a decoding network according to the optimized keyword model and the absorption model; performing keyword searching on a received voice signal to be detected by using the decoding network; outputting a search result. By using the language-irrelevant keyword search method and system, the keyword search rate can be improved under the condition that the training data samples of keywords are limited.

Description

technical field [0001] The invention relates to the technical field of voice keyword recognition, in particular to a language-independent keyword retrieval method and system. Background technique [0002] Voice keyword recognition refers to judging from a given voice file or data whether the voice data contains a specific keyword, and determining the position information where the keyword appears. The current mainstream speech keyword recognition is mainly based on speech recognition technology. First, the speech recognizer related to the speech language is used to recognize the text content contained in the speech, and then the specific keyword text and the location information where it appears are retrieved from the text content. Wait. In this method, users can define new keywords more conveniently, which has better scalability. However, since the development and training of the speech recognizer needs to build the acoustic model and language model of the corresponding l...

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): G06F17/30
CPCG06F16/683G06F16/686
Inventor 刘俊华魏思胡国平胡郁
Owner IFLYTEK 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