Unlock instant, AI-driven research and patent intelligence for your innovation.

Audio recognition method and device

An audio recognition and audio technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of time-consuming and low-efficiency data processing, and achieve the effects of improving data processing efficiency, reducing intermediate processes, and saving maintenance costs

Pending Publication Date: 2022-06-24
GUANGZHOU YOUMI INFORMATION TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Traditional multimodal knowledge graphs or entity recognition methods and classifications often need to convert audio data into corresponding texts, and then use commonly used entity recognition models and classification models to process the texts. Two steps require three models for processing. Data processing is time-consuming and inefficient

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 recognition method and device
  • Audio recognition method and device
  • Audio recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0086] see figure 1 , figure 1 It is a schematic flowchart of an audio recognition method disclosed in an embodiment of the present invention. in, figure 1 The described audio recognition method is applied in a data processing system, such as a local server or a cloud server for audio recognition management, which is not limited in the embodiment of the present invention. like figure 1 As shown, the audio recognition method may include the following operations:

[0087] 101. Acquire to-be-processed audio information.

[0088] 102. Preprocess the audio information to be processed to obtain first voice data feature information.

[0089] 103. Use an audio recognition model to perform recognition processing on the feature information of the first voice data to obtain target audio recognition information.

[0090] In the embodiment of the present invention, the above-mentioned target audio identification information includes M pieces of audio identification result information...

Embodiment 2

[0108] see figure 2 , figure 2 It is a schematic flowchart of another audio recognition method disclosed in an embodiment of the present invention. in, figure 2The described audio recognition method is applied in a data processing system, such as a local server or a cloud server for audio recognition management, which is not limited in the embodiment of the present invention. like figure 2 As shown, the audio recognition method may include the following operations:

[0109] 201. Acquire to-be-processed audio information.

[0110] 202. Preprocess the audio information to be processed to obtain first voice data feature information.

[0111] 203. Obtain an audio training set.

[0112] In the embodiment of the present invention, the above-mentioned audio training set includes several pieces of audio training information.

[0113] 204. Use the audio training set to train a preset first training model to obtain an audio recognition model.

[0114] 205. Use an audio recog...

Embodiment 3

[0184] see image 3 , image 3 It is a schematic structural diagram of an audio recognition device disclosed in an embodiment of the present invention. in, image 3 The described apparatus can be applied to a data processing system, such as a local server or a cloud server for audio recognition management, which is not limited in this embodiment of the present invention. like image 3 As shown, the apparatus may include:

[0185] an acquisition module 301, configured to acquire audio information to be processed;

[0186] a first processing module 302, configured to preprocess the audio information to be processed to obtain first voice data feature information;

[0187] The second processing module 303 is configured to use an audio recognition model to recognize and process the feature information of the first voice data to obtain target audio recognition information; the target audio recognition information includes M pieces of audio recognition result information; M is a...

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 an audio recognition method and device. The method comprises the following steps: acquiring audio information to be processed; preprocessing the to-be-processed audio information to obtain first voice data feature information; performing recognition processing on the first voice data feature information by using an audio recognition model to obtain target audio recognition information; the target audio recognition information comprises M pieces of audio recognition result information; m is a positive integer greater than or equal to 3. Visibly, the to-be-processed audio information can be pre-processed, and then the audio identification model is used for further identification processing to obtain the target audio identification information, so that effective entity information can be directly extracted from the audio and the audio is classified, the intermediate process of data processing is reduced, and the data processing efficiency is improved. The error influence of converting the audio data into the text data is avoided, the data processing efficiency is improved, and the maintenance cost is saved.

Description

technical field [0001] The present invention relates to the technical field of audio processing, and in particular, to an audio recognition method and device. Background technique [0002] Traditional multimodal knowledge graphs or entity recognition methods and classifications often need to convert audio data into corresponding texts, and then use commonly used entity recognition models and classification models to process the text. Two steps require three models to process, The data processing process is time-consuming and inefficient. Therefore, an audio recognition method and device are provided to directly extract effective entity information from audio and classify audio, reduce the intermediate process of data processing, avoid being affected by errors in converting audio data into text data, improve data processing efficiency and Saving maintenance costs is particularly important. SUMMARY OF THE INVENTION [0003] The technical problem to be solved by the present...

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): G10L15/22G10L15/02G10L15/06G10L15/16
CPCG10L15/22G10L15/063G10L15/02G10L15/16
Inventor 黄于晏钟艺豪陈第
Owner GUANGZHOU YOUMI INFORMATION TECH