Cipher text speech perception hashing and retrieving scheme based on time-frequency domain trend change

A technology that perceives hashing and trend changes. It is applied in speech analysis, special data processing applications, instruments, etc. It can solve problems such as low efficiency, and achieve the effect of improving matching efficiency, improving efficiency, and being easy to apply in practice.

Inactive Publication Date: 2015-08-12
SOUTHWEST JIAOTONG UNIV
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To sum up, the existing perceptual hashing algorithm blindly pursues the robustness of feature extraction, and does not start from the perspective of practical application, and its efficiency is low in large-scale applications; the increase in the amount of cloud ciphertext voice data has brought rapid , Accurate retrieval poses challenges

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
  • Cipher text speech perception hashing and retrieving scheme based on time-frequency domain trend change
  • Cipher text speech perception hashing and retrieving scheme based on time-frequency domain trend change
  • Cipher text speech perception hashing and retrieving scheme based on time-frequency domain trend change

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The technical solution of the present invention will be further described below in combination with appendices and embodiments.

[0036] 1. Perceptual hash generation

[0037] The perceptual hash extraction process is divided into two parts: time domain analysis and frequency domain analysis. The time-frequency domain extracts the perceptual hash separately and then crosses and combines them to form the final perceptual hash summary. The process block diagram is as follows figure 1 shown.

[0038] 1. Time domain aware hash generation:

[0039] (1) Carry out non-overlapping framing of voice signals, and the frame length is 20ms, which can be set according to actual use requirements;

[0040] (2) To calculate the short-term energy of each frame, for the convenience of calculation, the relatively simple sum of the absolute value of the short-term amplitude is used instead. use a p (q) represents the value of the qth sampling point in the pth frame of speech, m is the n...

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 cipher text speech perception hashing and retrieving scheme based on time-frequency domain trend change. A piece of speech is divided into a time domain part and a frequency domain part for extracting perception hash, the speech is encrypted by a high-efficiency chaotic XOR encryption algorithm adapting to large-scale data, and a perception hash sequence is embedded into the least significant bit of the cipher text speech by the digital watermarking technology to generate a cipher text speech library and a system perception hash table. The cipher text speech library and the perception hash table are uploaded to the cloud. During retrieval, a perception hash sequence is extracted from an index speech provided by a user, the abstract sequence is submitted to a cloud server as an index, and matching retrieval is carried out in the system hash table of the cloud. When the perception hash sequence is matched with a perception hash value in the system hash table, a cipher text speech corresponding to the hash abstract in the hash table is returned to the user, and retrieval succeeds. Rapid and accurate retrieval of an encrypted speech in the cloud is realized. According to the method, weight distinguishing is carried out, matching is carried out successively, and therefore, the matching efficiency in large-scale application is improved.

Description

technical field [0001] The present invention relates to a novel voice-aware hashing scheme and content-based ciphertext voice retrieval scheme. Background technique [0002] Speech-aware hashing algorithm is to map a single item of speech data set into a concise digital summary, and meet the requirements of discrimination, robustness, one-way, summarization and security. Speech-aware hashing technology has a wide range of applications, such as speech recognition, retrieval and authentication. With the popularization of the Internet and the rapid development of computer storage capacity, the number of voices is also increasing rapidly. How to better adapt the voice-aware hashing technology to such a rapidly increasing number of voices has become an urgent problem to be solved. The emergence of cloud computing provides a new idea for the storage of large-scale voice data. However, in a cloud environment, user data is stored in a remote server outside the firewall. From a cry...

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 Applications(China)
IPC IPC(8): G10L19/02G06F17/30H04L29/06
Inventor 王宏霞郝广洋
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