Voice similarity calculation method and device based on greedy algorithm

A technology of similarity calculation and greedy algorithm, which is applied in speech analysis, speech recognition, instruments, etc., and can solve problems such as large amount of computation

Pending Publication Date: 2020-03-17
CANAAN BRIGHT SIGHT CO LTD
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem in the prior art that the amount of calculation is too large when using the DTW algorithm to calculate the voice similarity, the present invention provides a v

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 similarity calculation method and device based on greedy algorithm
  • Voice similarity calculation method and device based on greedy algorithm
  • Voice similarity calculation method and device based on greedy algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] The principle and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present invention, rather than to limit the scope of the present invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0082] exemplary method

[0083] The embodiment of the present invention proposes a voice similarity calculation method based on a greedy algorithm, figure 1 is a schematic flowchart of a similarity calculation method based on a greedy algorithm according to an embodiment of the present invention. Such as figure 1 As shown, the method includes S110~S150:

[0084] S110: Obtain the test sequence V=(V 1 ,V 2 ,...,V N ) and template sequence U=(U 1 ,U ...

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 embodiment of the invention provides a voice similarity calculation method and device based on a greedy algorithm. The method comprises the following steps: 1, obtaining a test sequence V and a template sequence U, sequentially intercepting element groups (Vn, Vn + 1) in the test sequence as an nth local test sequence V'n based on the sliding window, and dynamically intercepting continuous i frames of the template sequence to serve as corresponding local template sequences, establishing a local similarity matrix based on each local test sequence and the corresponding local template sequence, and further obtaining the global similarity between the test sequence and the template sequence by utilizing a greedy algorithm. The greedy thought is utilized, the global optimal path is obtainedby calculating the local optimal path, and the calculation amount in DTW operation is remarkably reduced.

Description

technical field [0001] The invention relates to the field of voice recognition, in particular to a method and device for calculating voice similarity based on a greedy algorithm. Background technique [0002] This section is intended to provide a background or context for implementations 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] In recent years, with the development of human-computer information interaction technology, speech recognition technology has shown its importance. The Dynamic Time Warping (DTW) algorithm is a commonly used matching algorithm in speech recognition. The DTW algorithm is based on the idea of ​​dynamic programming (DP), and calculates two time series by extending and shortening the time series. It can effectively solve the problem of inconsistency between the speed of the test voice and the template voice. [0004] The traditional DTW algorithm is ...

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): G10L15/10G10L15/28G10L25/27
CPCG10L15/10G10L15/28G10L25/27
Inventor 吴威张楠赓
Owner CANAAN BRIGHT SIGHT 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