Method, device and equipment for identifying multiple paths of voice as well as readable storage medium

A speech recognition and speech signal technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problem of low speech recognition rate

Pending Publication Date: 2019-06-21
APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECH CO LTD
View PDF12 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a multi-channel speech recognition method, device, equipment and readable storage medium to solve the problem of low speech recognition rate of the speech recognition method on the vehicle in the prior art

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
  • Method, device and equipment for identifying multiple paths of voice as well as readable storage medium
  • Method, device and equipment for identifying multiple paths of voice as well as readable storage medium
  • Method, device and equipment for identifying multiple paths of voice as well as readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] figure 1 It is a flow chart of the multi-channel speech recognition method provided by Embodiment 1 of the present invention. The embodiment of the present invention provides a multi-channel voice recognition method to solve the problem that the voice recognition rate of the vehicle voice recognition method in the prior art is very low. The method in this embodiment is applied to a voice recognition device. The voice recognition device may be a vehicle-mounted terminal device installed on a vehicle, or may be a computer device capable of communicating with a vehicle-mounted terminal device and performing voice recognition. In other In this embodiment, the method may also be applied to other devices, and this embodiment uses a speech recognition device as an example for schematic illustration.

[0031] Such as figure 1 As shown, the specific steps of the method are as follows:

[0032] Step S101 , receiving audio data collected by multiple microphone arrays, each micr...

Embodiment 2

[0048] figure 2 It is a flow chart of the multi-channel speech recognition method provided by Embodiment 2 of the present invention. On the basis of the first embodiment above, in this embodiment, according to the position of each microphone array relative to the corresponding audio collection area, each channel of audio data is subjected to beamforming processing, and each channel of audio data corresponding to the corresponding audio collection area is obtained. Before the audio signal of the audio signal, it also includes: obtaining the position of each microphone array relative to the corresponding audio collection area. Carrying out speech recognition on the speech signals corresponding to each audio collection area, after obtaining the recognition result corresponding to each audio collection area, also includes: calculating the average energy amplitude of the speech signal corresponding to each audio collection area; removing the average energy amplitude less than the ...

Embodiment 3

[0092] image 3 It is a schematic structural diagram of a multi-channel speech recognition device provided in Embodiment 3 of the present invention. The multi-channel speech recognition device provided in the embodiment of the present invention can execute the processing flow provided in the embodiment of the multi-channel speech recognition method. Such as image 3 As shown, the multi-channel speech recognition device 30 includes: a data acquisition module 301 , a beamforming module 302 , an interference suppression processing module 303 and a speech recognition module 304 .

[0093] Specifically, the data acquisition module 301 is configured to receive audio data collected by multiple microphone arrays, and each microphone array points to an audio collection area in the vehicle for collecting one audio data.

[0094] The beamforming module 302 is configured to perform beamforming processing on each channel of audio data according to the position of each channel of the micr...

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 provides a method, a device and equipment for identifying multiple paths of voice as well as a readable storage medium. The method comprises the following steps: receiving audio data collected by multiple paths of microphone arrays, carrying out wave beam formation treatment on each path of audio data to obtain audio signals corresponding to audio collection areas in each path of audio data, and weakening audio signals in other directions of the path of audio data; carrying out interference inhibition treatment on multiple paths of audio signals to obtain voicesignals corresponding to each audio collection area, reducing interference of noise signals of other audio collection areas on the path of voice signals, carrying out voice identification of the voicesignals to obtain a voice identification result corresponding to each audio collection area, and improving identification rate of the voice identification; inhibiting mutual interference among the multiple paths of voice signals when multiple people talk at the same time to obtain a voice identification result corresponding to each audio collection position, and improving the efficiency and accuracy of voice identification.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of speech recognition, and in particular to a multi-channel speech recognition method, device, equipment and readable storage medium. Background technique [0002] At present, the car machine on the vehicle is only equipped with a dual-channel microphone in the front row, including two microphones for the left and right channels, which are mainly used to collect audio data near the driving position. Recognition, to recognize recognition words such as instructions issued by the driver to the car machine. [0003] However, if the passenger sitting in the passenger seat or the rear seat of the vehicle sends out recognition words to the car, the quality of the audio data collected by the microphone is poor because the sound source is far away from the microphone, resulting in a very low speech recognition rate, especially in When many people speak the identifying language at the same t...

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): G10L15/02G10L15/26G10L25/03
Inventor 陈建哲彭汉迎欧阳能钧
Owner APOLLO INTELLIGENT CONNECTIVITY (BEIJING) 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap