Speech feature extraction method based on quantum Fourier transform

A Fourier transform and speech feature technology, applied in speech analysis, instruments, etc., can solve problems such as high time cost, inability to better meet real-time requirements, and high time complexity of short-time Fourier transform

Pending Publication Date: 2021-04-16
XIDIAN UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, using the short-time Fourier transform to convert the speech signal from the time domain to the frequency domain has the disadvantage that the time complexity of the algorithm using the short-time Fourier tr

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
  • Speech feature extraction method based on quantum Fourier transform
  • Speech feature extraction method based on quantum Fourier transform
  • Speech feature extraction method based on quantum Fourier transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0037] refer to figure 1 , the present invention comprises the following steps:

[0038] Step 1) Initialize the quantum computer parameters:

[0039] Initialize the quantum logic gates of the quantum computer as Hadamard and CR a,b , the state space quantum number is n, and the decimal quantum state is n≥1, Hadamard and CR a,b The expressions are respectively:

[0040]

[0041]

[0042] Among them, a represents the target bit, b represents the control bit, and θ a,b Indicates the phase shift of a, θ a,b =2πb / 2 a-b+1 ;

[0043] Step 2) discretize the speech signal:

[0044] Acquisition of voice signals in M ​​time domains A={A i |1≤i≤M}, and for each speech signal A i Carry out N times of sampling, the number of samples N and the voice signal A i The length T of is related to the sampling time interval δ, and its formu...

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 provides a speech feature extraction method based on quantum Fourier transform, and aims to improve the speed of speech signal feature extraction on the premise of not reducing the resolution of speech signal feature extraction. The method comprises the following steps of: 1) initializing quantum computer parameters; 2) discretizing speech signals; 3) obtaining a binary quantum state of each time domain speech signal segment through a quantum computer; 4) performing quantum Fourier transform on the binary quantum state through the quantum computer; 5) performing quantization coding on a time domain speech signal segment digital matrix through the quantum computer; and 6) obtaining a feature extraction result of the speech signals through the quantum computer. Quantum Fourier transform is realized by using a quantum logic gate, conversion of each binary quantum state is completed, which is equivalent to the completion of multiple addition, subtraction, multiplication and division operations at the same time; the calculation frequency is obviously reduced; and the speech feature extraction speed is effectively improved.

Description

technical field [0001] The invention belongs to the field of speech feature extraction, and relates to a speech feature extraction method based on quantum Fourier transform, which can realize the feature extraction of speech signals and improve the speed of speech feature extraction. Background technique [0002] Language is a unique communication method for human beings. Speech feature extraction is an important means to realize human-computer interaction. Speech features can help computers understand human language. Using computers to correctly extract language signal features is an important problem in computer development technology. Resolution and minimum detection time cost are important indicators of speech feature extraction. As speech recognition technology is widely used in various fields such as national security, telephone banking, social networking, and military intelligence, people have more and more real-time requirements for speech feature extraction. Therefo...

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): G10L25/03
CPCY02D10/00
Inventor 李阳阳杨丹青刘睿娇毛鹤亭赵裴翔赵逸群焦李成李玲玲
Owner XIDIAN 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