Voice late reverberation suppression method and system

A speech and reverberation technology, applied in speech analysis, instruments, etc., can solve problems such as the reverberation environment that cannot adapt to time-varying, achieve a good speech environment, avoid excessive reduction or insufficient suppression, and enhance the effect.

Pending Publication Date: 2020-05-19
XIAMEN YEALINK NETWORK TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to overcome the deficiencies in the prior art that the late speech reverberation suppression method cannot adapt to the time-varying reverberation environment, and propose a speech late reverberation suppression method and system, which can adapt to the time-varying reverberation environment and stabilize Suppresses late reverb, which in turn can enhance the effect of late reverb suppression

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
  • Voice late reverberation suppression method and system
  • Voice late reverberation suppression method and system
  • Voice late reverberation suppression method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] combine figure 1 Shown, a kind of speech late reverberation suppressing method of the present invention comprises the following steps:

[0039] The reverberation speech signal in the room is collected, and the reverberation attenuation parameters are extracted; the specific process of extracting the reverberation attenuation parameters is as follows:

[0040] (1) Carry out windowing and framing processing to the reverberation speech signal and carry out short-time Fourier transform;

[0041] (2) Calculate the amplitude spectrum of each frame and divide the amplitude spectrum evenly into H frequency bands; in the present embodiment, the amplitude spectrum is evenly divided into 40 frequency bands. It is worth noting that the process of calculating the amplitude spectrum of each frame is: The frame is subjected to windowing processing, and then short-time Fourier transform is performed to obtain several complex values, and then the sum of the squares of the complex value...

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, which belongs to the technical field of voice processing, discloses a voice late reverberation suppression method and system. The method comprises the following steps: acquiring an indoor reverberation voice signal, and extracting a reverberation attenuation parameter; calculating a reverberation spectrum characteristics a according to the reverberation attenuation parameter; calculating a voice spectrum feature b after reverberation suppression according to the reverberation spectrum feature a and naive spectrum subtraction; and then performing interpolation calculation on thevoice frequency spectrum feature b, restoring the voice frequency spectrum feature b by using the phase feature of the reverberation voice signal so as to obtain a waveform voice, and outputting the waveform voice. The system comprises an acquisition unit, a calculation unit, a transmission unit and a terminal, the acquisition unit is electrically connected with the calculation unit, and the calculation unit and the terminal are respectively connected with the transmission unit. Therefore, the defect that a voice late reverberation suppression method cannot adapt to a time-varying reverberation environment in the prior art is overcome, and the voice late reverberation suppression method and system can adapt to the time-varying reverberation environment and stably suppress late reverberation.

Description

technical field [0001] The present invention relates to the technical field of speech processing, and more specifically, to a method and system for suppressing late reverberation in speech. Background technique [0002] Reverberation is the diffuse reflection of sound waves between obstacles such as walls, ceilings, and furniture when they propagate indoors. The energy of each reflection of sound waves is weakened by obstacles. The process of absorbing and finally disappearing. [0003] In acoustics, T60 is used to estimate the reverberation time of a room. Usually, the reverberation time of small and medium meeting rooms does not exceed 1s. In real-time conference communication equipment, the sound source emits sound, and the sound source picked up directly by the microphone is called direct sound (without any reflection, the sound source directly points to the microphone, and is picked up by the microphone as reverberation after reflection), after the direct sound arrives...

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): G10L21/0208
CPCG10L21/0208G10L2021/02082
Inventor 方泽煌康元勋
Owner XIAMEN YEALINK NETWORK TECH
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