Digital speech perception hash method based on formant frequency

A perceptual hashing and formant technology, applied in speech analysis, instruments, etc., can solve the problems of not considering perceptual hashing efficiency and complexity, algorithm complexity and practical application efficiency, etc., so as to save the amount of calculation , improve retrieval efficiency, and improve matching efficiency

Inactive Publication Date: 2016-07-06
SOUTHWEST JIAOTONG UNIV
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the performance of the existing perceptual hashing algorithm is constantly improving, it has not been considered from the perspective of big data application background, and the balance between algorithm complexity and practical application efficiency cannot be achie

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
  • Digital speech perception hash method based on formant frequency
  • Digital speech perception hash method based on formant frequency
  • Digital speech perception hash method based on formant frequency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The technical solution of the present invention will be further described below in combination with appendices and embodiments.

[0025] The invention extracts rough features and detailed features respectively from the voice signal. When extracting rough features, the speech is analyzed in the frequency domain, and the formant frequency of the speech is selected as a feature, and the non-overlapping frame method is used to extract the first k formants of each frame, which are respectively compared with the median of the corresponding formant frequency. Quantization is the coarse perceptual hash sequence that reflects the coarse feature of speech; The present invention adopts linear predictive coding (LPC) algorithm to extract the formant frequency of speech, why choose LPC algorithm because LPC is the most optimal in speech signal analysis and speech signal coding application One of the effective ways, it provides a set of concise speech signal model parameters to accur...

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 digital speech perception hash method based on formant frequency. The method is used for speech retrieval in a big data background, and the format frequency capable of reflecting timbre characteristics of speakers and time domain energy differences having the strong robustness can be respectively extracted to be used as the detail characteristics of the speech segments. During the matching process, the speech rough characteristics can be matched, and the speech segments having the timbres, which are similar to that of the target speech, can be screened out, and then the speeches having the similar timbres can be screened out for the matching of the detail characteristics, and at last, the accurate matching result can be acquired. When the method is used for the mass speech signal processing, a lot of unnecessary calculation amount can be saved, and the matching efficiency can be improved obviously.

Description

technical field [0001] The invention relates to a novel voice perception hash scheme aiming at how to improve the processing efficiency of massive voice signals under the background of big data application. Background technique [0002] With the advent of the "Internet +" era, the rapid development of mobile Internet, cloud computing, big data and artificial intelligence, people are eager to interact with computers directly through voice, which makes large-scale storage and processing of voice a research hotspot. As the technical support of information services such as multimedia content identification, retrieval, and authentication, perceptual hashing will face two major problems: how to reduce computational complexity and computational efficiency. The current perceptual hashing algorithm mainly focuses on the performance of feature extraction methods and hash construction methods, without considering the efficiency and complexity of applying perceptual hashing in practice ...

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): G10L25/54
CPCG10L25/54
Inventor 王宏霞任刘姣
Owner SOUTHWEST JIAOTONG UNIV
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