Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Speech enhancement method and device, speech interaction method and device, program product and equipment

A voice enhancement and voice interaction technology, applied in the computer field, can solve the problems of multiple interference sources, low signal-to-noise ratio of the original signal of the microphone, and inability to perform noise reduction processing, and achieve noise suppression, low signal-to-noise ratio, and effective voice enhancement. Effect

Pending Publication Date: 2022-06-21
ALIBABA GRP HLDG LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For sweeping robots, there are great difficulties in directly performing voice interaction with the equipment: on the one hand, the mechanical noise, motor noise, and vacuum cleaner noise emitted by the sweeper itself are relatively large when the sweeper is working; however, the microphone is installed on the main body of the sweeper In general, the distance to the noise source is relatively close, so the signal-to-noise ratio of the original signal received by the microphone is extremely low, and there are many kinds of devices on the sweeper that can emit noise, and the distance to the microphone is relatively close, which belongs to the problem of multiple interference sources
On the other hand, the sweeping machine will move during the working process, resulting in the real-time dynamic signal received, it is difficult to determine the direction of the voice source in real time, and thus cannot perform effective noise reduction processing

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 enhancement method and device, speech interaction method and device, program product and equipment
  • Speech enhancement method and device, speech interaction method and device, program product and equipment
  • Speech enhancement method and device, speech interaction method and device, program product and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] like figure 1 As shown in the figure, the sweeping robot will move continuously during the working process. The figure exemplarily shows the motion trajectory of the cleaning robot in the four time periods formed from t1 to t5. The large circle in the picture represents the robot vacuum cleaner, and the small circle with serrated edges outside the large circle represents the noise source of the robot vacuum cleaner, such as motors, vacuum cleaners, etc. As shown in the picture, no matter how the robot moves and / or rotates, the noise The position of the sound source on the robot vacuum cleaner is fixed. The bottom of the picture is the voice sound source, which is generally issued by the user. figure 1 In the scenario shown, it is assumed that the user's position is stationary and the cleaning robot is moving. It can be seen from the figure that as the moving position of the sweeping robot changes, its positional features such as distance and direction relative to the...

Embodiment 2

[0063] like Figure 4 As shown, it is a schematic structural diagram of a voice enhancement processing device according to an embodiment of the present invention. The device can be applied to a movable device that needs to perform voice interaction, and can also be applied to the server side. The server obtains the microphone from the device side through the network. signal and perform speech enhancement processing. The specific processing process is as follows:

[0064] The noise feature extraction module 11 is configured to collect the microphone signal in the first time period, and extract the noise feature according to the microphone signal. wherein the first time period may correspond to figure 1 During the time period from t2 to t3 in , the microphone signal is regarded as a noise signal for feature extraction. The extracted noise features may be specifically a noise covariance matrix. Specifically, the processing in this part may further include: collecting microphon...

Embodiment 4

[0071] The embodiment of the present invention provides a voice interaction method, which can be applied to a movable device that needs to perform voice interaction, or can be applied to the server side, where the server obtains the microphone signal from the device side through the network and returns the processing result For the device, it specifically includes: S201: Collect sound signals. Specifically, the sound signal can be collected through the microphone array on the device.

[0072] S202: Perform voice enhancement processing on the sound signal, extract noise features during the voice enhancement processing, and update a beamformer for voice enhancement processing according to the noise features after a period of time. Wherein, the speech enhancement processing process of this step may adopt the specific processing manner mentioned in the previous embodiment.

[0073] S203: Perform voice command recognition on the voice signal after voice enhancement processing, and...

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 relates to a voice enhancement method and device, a voice interaction method and device, a program product and equipment, and the method comprises the steps: collecting a microphone signal in a first time period, and extracting a noise feature according to the microphone signal; after a second time period, updating the beam former according to the noise characteristics; and performing voice enhancement processing on subsequent microphone signals by using the updated beam former. According to the embodiment of the invention, by utilizing the characteristics that the noise signal characteristics of the equipment are slightly changed and the external voice signal characteristics are greatly changed due to the change of the sound source position in the equipment moving process, the noise characteristic acquisition and the wave beam former updating can be updated by setting the time interval between the noise characteristic acquisition and the wave beam former updating. Useful voice components are prevented from being eliminated, so that the voice enhancement performance is improved.

Description

technical field [0001] The present application relates to a voice enhancement and interaction method, device, program product and device, and belongs to the field of computer technology. Background technique [0002] Speech enhancement refers to the technology of extracting useful speech signals from the noise background and suppressing and reducing noise interference when the speech signal is interfered with or even submerged by various noises. Speech enhancement is widely used in various human-computer interaction scenarios that require speech recognition. [0003] As an important device in the smart home, the sweeping robot is gradually developing in the direction of voice and intelligence. For the sweeping robot, it is very difficult to directly interact with the device. On the one hand, the mechanical noise, motor noise, and noise of the vacuum cleaner emitted by the sweeper are louder when it is working. However, the microphone is installed on the main body of the swe...

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): G10L21/0216
CPCG10L21/0216G10L2021/02166
Inventor 纳跃跃王子腾刘章李韵乔刚田彪付强
Owner ALIBABA GRP HLDG LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com