Vehicle-mounted voice recognition method, system and device and storage medium

A vehicle-mounted voice and recognition method technology, applied in voice recognition, voice analysis, instruments, etc., can solve the problem that the isolated word recognition algorithm has not been ideally applied, so as to improve the efficiency of voice recognition, reduce the workload, and improve the accuracy of voice recognition Effect

Pending Publication Date: 2022-04-22
CHONGQING COLLEGE OF ELECTRONICS ENG
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, in speech recognition technology at home and abroad, there are few studies on the speed and accuracy of isolated word recognition, which also makes the isolated word recognition algorithm not ideally applied in actual life and production.

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
  • Vehicle-mounted voice recognition method, system and device and storage medium
  • Vehicle-mounted voice recognition method, system and device and storage medium
  • Vehicle-mounted voice recognition method, system and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Embodiment 1 is basically as attached figure 1 Shown:

[0043] A vehicle-mounted speech recognition method, comprising the following steps:

[0044] S100. Collect voice signals. In this implementation, a microphone is used to collect voice signals.

[0045] S200. Perform preprocessing on the collected speech signal to generate effective speech segments. Since the voice signal is a typical non-stationary random signal, it is easily affected by respiratory airflow, environmental background noise, and current noise. Therefore, it is necessary to preprocess the voice signal collected by the hardware circuit before further analysis of the voice signal. . In this embodiment, the preprocessing includes filter processing, pre-emphasis processing, frame division and windowing processing, and endpoint detection. The preprocessed speech signal has less noise interference, purer signal, and more stable characteristic parameters, which is beneficial to the subsequent speech reco...

Embodiment 2

[0065] Embodiment 2 is basically as attached figure 1 Shown:

[0066] The basic principle of embodiment 2 is the same as that of embodiment 1, and the difference is that embodiment 2 further includes S600, which recognizes sleep characteristic sounds in the voice signal, and generates sleep recognition results; generates control sound effects according to the sleep recognition results. Specifically, the speech signal is compared with a pre-stored sleep characteristic speech database, the sleep characteristic sound in the speech signal is recognized, and a sleep recognition result is generated. In this embodiment, the sleep feature sound library includes the following sleep feature sounds: snoring and teeth grinding. When it is recognized that the user is asleep, the control sound effects of "close the window" and "increase the temperature of the air conditioner" are generated.

[0067] The vehicle-mounted voice recognition system uses the above-mentioned vehicle-mounted voic...

Embodiment 3

[0071] Embodiment 3 is basically as attached figure 1 Shown:

[0072] The basic principle of embodiment 3 is the same as that of embodiment 2. The difference is that in S600 of embodiment 3, the breathing sound in the voice signal is recognized to generate the user's respiratory rate, and the sleep recognition result is generated according to the change of the user's respiratory rate. The principle is that the breathing rate of the user in the sleeping state is relatively slower than that in the awake state. Therefore, in this solution, the change of the breathing rate of the user is detected, so as to perform more accurate recognition of the sleeping state.

[0073] The vehicle-mounted voice recognition system uses the above-mentioned vehicle-mounted voice recognition method.

[0074] The vehicle-mounted speech recognition device includes a processor; and a memory configured as computer-executable instructions, and the computer-executable instructions cause the processor to ...

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 the technical field of voice recognition, in particular to a vehicle-mounted voice recognition method, system and device and a storage medium, and the method comprises the following steps: S100, collecting a voice signal; s200, preprocessing the collected voice signal to generate an effective voice segment; s300, performing feature parameter extraction on the effective voice segments to generate a test template; s400, comparing the test template with a pre-stored reference template by using a DTW algorithm, and generating a comparison result; and S500, generating an identification result according to a comparison result. By adopting the scheme, the effective voice segments in the voice signals can be recognized, and the isolated word recognition efficiency and accuracy are improved.

Description

technical field [0001] The present invention relates to the technical field of voice recognition, in particular to a vehicle-mounted voice recognition method, system, device and storage medium. Background technique [0002] Language is the most natural and important communication tool between people, and it is also one of the important ways for human beings to obtain information. Speech recognition is one of the core technologies of the next generation of human-computer interaction, and it is also an important technical basis for intelligent and humanized machines. It is of great significance in practical applications to allow machines to perform various operations and even communicate with people according to human voice commands. The voice recognition technology can make the multi-layer input operation with redundant scale and complex form simple and convenient, and the user can master the operation method of the equipment without special professional operation training. ...

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): G10L15/02G10L15/06G10L15/22G10L25/51
CPCG10L15/02G10L15/06G10L15/22G10L25/51G10L2015/0631
Inventor 张慧敏
Owner CHONGQING COLLEGE OF ELECTRONICS ENG
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