Speech feature extraction method based on quantum Fourier transform

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...

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 transform is high, which leads to the fact that in the era of big data, when faced with a large amount of speech data , its feature extraction takes a high time cost, so it cannot better meet the real-time requirements

Images