Binaural speech reverberation eliminating method and device based on speech presence probability and consistency

A technology of occurrence probability and consistency, applied in speech analysis, instruments, etc., can solve problems such as large structure size, large calculation amount, and complex system calculation

Active Publication Date: 2018-12-11
PEKING UNIV SHENZHEN GRADUATE SCHOOL
View PDF8 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But its disadvantage is that the structure size is huge, the calculation

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
  • Binaural speech reverberation eliminating method and device based on speech presence probability and consistency
  • Binaural speech reverberation eliminating method and device based on speech presence probability and consistency
  • Binaural speech reverberation eliminating method and device based on speech presence probability and consistency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0128] The present invention will be clearly and completely described below in conjunction with the embodiments and accompanying drawings.

[0129] The database used in this embodiment is relatively authoritative and one of the most widely used databases in the field of speech enhancement in the world. The pure speech is taken from the TSP database, and a total of 80 sentences are used for testing. The signal received by the microphone is obtained by convolving the pure speech signal on the room impulse response provided by the Air (Aachen Impulse Response) database. The Air impulse response database was recorded by the Institute of Communication Systems of RWTH Aachen University in Germany using HMS2 to simulate artificial heads, including offices, conference rooms, lecture halls and other different types of scenes, and is used for the research of signal processing algorithms in reverberant environments. The two microphones are located on the left ear and the right ear of th...

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 binaural speech reverberation eliminating method and device based on the speech presence probability and consistency. The method comprises the steps of 1) performing time delay compensation on speech signals received by two microphones to obtain speech signals aligned in time; 2) performing windowing and framing processing, and transforming the speech signals from the time domain to the frequency domain through Fourier transform; 3) estimating a reverberation power spectrum of a low frequency part based on the speech presence probability; 4) calculating the consistency of different signal components of the speech signals; 5) estimating a reverberation power spectrum of a high frequency part based on the consistency; 6) estimating a reverberation power spectrum combining high and low frequencies according to a division threshold of high and low frequency bands; 7) calculating a final reverberation power spectrum by using a recursive smoothing algorithm; 8) obtaining frequency domain signals with the reverberation being eliminated through a gain function; and 9) obtaining time domain signals with the reverberation being eliminated by using short-time inverseFourier transform. According to the invention, the reverberation on the whole frequency band can be effectively eliminated, and the quality of speech perception is improved.

Description

technical field [0001] The invention belongs to the technical field of audio signal processing and computer hearing, and in particular relates to a method and device for reverberating speech with two microphones in an environment with reverberation. The reverberation of the high-frequency part is removed by using the voice consistency model, which can effectively remove the reverberation in the entire frequency band and improve the quality of speech perception. Background technique [0002] Binaural audio naturally has many advantages for communication and multimedia experiences. In the daily interaction between people, auditory perception is one of the most effective and direct ways of interaction between people. However, in the actual environment, speech, as an important information carrier for communication between people and machines, is inevitably disturbed by reverberation, environmental noise, etc., which greatly reduces the clarity, intelligibility and comfort of sp...

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): G10L21/0208G10L21/0216G10L21/0232
CPCG10L21/0208G10L21/0216G10L21/0232G10L2021/02082G10L2021/02165
Inventor 刘宏王秀玲
Owner PEKING UNIV SHENZHEN GRADUATE SCHOOL
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