Audio signal processing method and system, audio interaction device and computer equipment

An audio signal processing and signal technology, applied in interconnection devices, speech analysis, telephone communication, etc., can solve the problems of unsatisfactory echo cancellation performance, convergence, echo and noise cancellation effects of intelligent audio interactive devices, etc.

Active Publication Date: 2017-06-27
SHANGHAI XIAOI ROBOT TECH CO LTD
View PDF5 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The echo cancellation technology based on the PBFDAF algorithm has been proved to be able to effectively cancel the echo and improve the quality of voice communication in the real-time communication of Internet telephony and web pages. However, the performance of echo cancellation in intelligent audio interactive devices is not satisfactory.
First of all, although the PBFDAF algorithm can reduce the echo generated by the speaker, it is basically ineffect

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
  • Audio signal processing method and system, audio interaction device and computer equipment
  • Audio signal processing method and system, audio interaction device and computer equipment
  • Audio signal processing method and system, audio interaction device and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] figure 2 It is a schematic flow chart of an audio signal processing method provided in Embodiment 1 of the present invention. This method is suitable for echo and noise processing on the picked-up audio input signal when an audio interaction device with an audio interaction function performs audio interaction. It may be executed by an audio signal processing system, wherein the system may be implemented by software and / or hardware, and generally integrated on an audio interaction device with an audio interaction function.

[0038] It should be noted that the audio interaction can be specifically understood as the voice interaction between the user and the audio interaction device, and the audio interaction device can be an electronic product with a voice interaction function such as an intelligent voice assistant, a smart home, and a voice navigator. .

[0039] Such as figure 2 As shown, the audio signal processing method provided by Embodiment 1 of the present inve...

Embodiment 2

[0052] image 3 It is a schematic flowchart of an audio signal processing method provided by Embodiment 2 of the present invention. The embodiment of the present invention is optimized on the basis of the above embodiment. In this embodiment, the noise signal in the audio residual signal will be Noise elimination, obtaining the audio enhancement signal after noise elimination, further optimized to: determine the audio residual according to the power spectrum of the audio residual signal and the predetermined noise power spectrum of the noise signal in the audio residual signal The first posterior signal-to-noise ratio and the priori signal-to-noise ratio of the signal; according to the first posteriori signal-to-noise ratio and the priori signal-to-noise ratio, determine the first attenuation coefficient of the noise signal in the audio residual signal ; Eliminate a noise signal in the audio residual signal according to the first attenuation coefficient, to obtain an audio enh...

Embodiment 3

[0114] Figure 4a It is a schematic flowchart of an audio signal processing method provided by Embodiment 3 of the present invention. The embodiments of the present invention are optimized based on the above embodiments. In this embodiment, after determining the difference between the audio input signal and the echo estimation signal as the audio residual signal of the audio input signal, further The optimization includes: determining an update factor of the frequency domain filter coefficient according to the audio reference signal and the determined audio residual signal; updating and saving the adaptive filter coefficient according to the update factor.

[0115] Further, after performing echo cancellation on the echo signal in the acquired audio input signal and obtaining the audio residual signal of the audio input signal, it further includes: detecting whether the audio input signal contains a user voice signal, and detecting the whether the audio reference signal contai...

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 embodiment of the invention discloses an audio signal processing method and system, an audio interaction device and computer equipment. The method includes the following steps: performing echo cancellation on an echo signal in an acquired audio input signal to obtain an audio residual error signal of the audio input signal; performing noise cancellation on a noise signal in the audio residual error signal to obtain an audio enhancing signal after noise cancellation; and performing residual noise signal detection on the audio enhancing signal, and if a residual noise signal exists in the audio enhancing signal, filtering out the residual noise signal. By utilization of the method, the echo signal and the environmental noise signal in the audio input signal during audio interaction can be removed, detection and filtering of residual noise are realized at the same time, influence of environmental noise on an audio interaction process is effectively suppressed, and an effect of cancelling echoes and noise in the audio interaction process is improved, thereby improving the performance of an audio interaction device in cancelling echoes and noise.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of audio signal processing, and in particular to an audio signal processing method, system, audio interaction device, and computer equipment. Background technique [0002] For an intelligent audio interaction device with a voice interaction function, it can not only accept the user's voice instructions through a microphone, but also broadcast feedback information to the user through a speaker. However, the sound broadcast by the speaker to the user will also be collected by the microphone again as an acoustic echo, thereby affecting the recognition and understanding of the user's voice by the interactive device, thereby reducing the working performance of the audio interactive device. In addition, in practical applications, due to the different hardware structures of intelligent audio interactive devices, the distances and installation methods of microphones and speakers are different, ...

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): G10L21/0208G10L21/0264G10L21/0232
CPCG10L21/0208G10L21/0232G10L21/0264G10L2021/02082H04M9/082
Inventor 余世经朱频频
Owner SHANGHAI XIAOI ROBOT TECH CO LTD
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