Vehicle-mounted speech control method and system based on deep learning

A technology of deep learning and in-vehicle voice, which is applied in voice analysis, voice recognition, instruments, etc., can solve problems such as recognition effect discount, and achieve the effect of improving accuracy

Inactive Publication Date: 2019-11-05
的卢技术有限公司
View PDF10 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The traditional speech recognition method mainly adopts the method of template matching, which can achieve a certain effect in the recognition of isolated words, but in the face of a large number of continuous speech expressions, the recognition effect is greatly reduced

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 speech control method and system based on deep learning
  • Vehicle-mounted speech control method and system based on deep learning
  • Vehicle-mounted speech control method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] refer to Figure 1~3 In this embodiment, it is an overall flow chart of a vehicle-mounted voice control method based on deep learning. Voice, as a carrier of language symbols, carries certain language meaning and rich inner feelings in the transmission process. Therefore, voice is the most direct and efficient way to transmit thoughts and express emotions between people. With the continuous development of intelligent information technology, compared with the traditional human-computer interaction with computers through hardware devices, human beings prefer to interact with smart devices such as computers directly through voice. Therefore, the study of extending the most convenient voice communication method in human daily communication to the intelligent voice interaction method between humans and hardware devices has always been a research topic that researchers pay close attention to and is extremely challenging. Several core technologies to realize human-computer vo...

Embodiment 2

[0077] refer to Figure 4 To illustrate, this embodiment proposes a vehicle voice control system based on deep learning, including a signal acquisition module 100 , a signal amplification circuit 200 , a voice recognition module 300 and a control module 400 . Specifically, the signal acquisition module 100, the signal acquisition module 100 is distributed and arranged in the vehicle, and is used to collect the user's audio signal in real time; the signal increasing circuit 200 is connected with the signal acquisition module 100, and is used to receive multiple signals generated by the signal acquisition module 100. The electrical signals are summed and amplified to provide an audio input signal; the speech recognition module 300 is connected to the signal amplification circuit 200, and the audio input signal is input to the speech recognition module 300 to generate a recognition result, and can match the recognition result in the instruction library according to the recognition...

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 a vehicle-mounted speech control method and system based on deep learning. The method comprises the steps as follows that signal collection modules collect real-time audio signals of a user in a vehicle; a signal amplification circuit receives electrical signals generated by the plurality of signal collection modules, sums and amplifies the signals, and then provides an audio input signal; a speech recognition module is provided, and the audio input signal is input into the speech recognition module to generate a recognition result; and a control module receives a matched command signal to execute a command. The vehicle-mounted speech control method and system have the beneficial effects that the speech recognition accuracy is improved to a certain degree by speechrecognition based on deep learning, the language intention expressed by the user in the vehicle can be better learned, and thus the action of the vehicle is more accurately controlled by speech.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a vehicle-mounted speech control system based on deep learning and a control method thereof. Background technique [0002] In recent years, with the development of deep learning, new breakthroughs and progress have been made in the field of speech recognition based on deep learning. Many new speech recognition models have emerged, which have significantly improved the recognition effect. At the same time, with the popularity of mobile devices, smart home devices, and vehicle information systems, speech recognition is increasingly appearing in people's daily life. [0003] The traditional speech recognition method mainly adopts the method of template matching, which can achieve a certain effect in the recognition of isolated words, but in the face of a large number of continuous speech expressions, the recognition effect is greatly reduced. Compared with tradit...

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): G10L15/22G10L15/02G10L15/06G10L15/08G10L25/45G10L25/30
CPCG10L15/22G10L15/02G10L15/063G10L15/08G10L25/45G10L25/30G10L2015/223
Inventor 张亮
Owner 的卢技术有限公司
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