Check patentability & draft patents in minutes with Patsnap Eureka AI!

In-vehicle circumstantial speech recognition

By monitoring vehicle function parameters and user interaction, identifying user expected functions and decoding voice commands, the ASR system solves the problem of voice ambiguity in vehicle control and improves the accuracy of function control and user experience.

Active Publication Date: 2009-06-24
GENERAL MOTORS LLC +1
View PDF4 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] One problem encountered with ASR-enabled vehicle function controls is that while such a system can correctly decode user input speech, it may incorrectly apply recognized speech to non- Intended Vehicle Functions
In other words, current ASR-capable vehicle function controls have significant difficulty disambiguating between speech used for one vehicle function and speech used for some other vehicle function
For example, a user might say "let me hear some traffic" to cause the vehicle radio to play music from the 1960s rock band Traffic, but with ASR A capable vehicle controller may misinterpret the request and instead cause another vehicle device to play a route traffic report
Thus, users of ASR-capable vehicles have become frustrated with the situation

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] An exemplary working environment such as figure 1 shown, and can be used to implement the situation-based speech recognition method disclosed herein. The method can be performed using any suitable telematics system, and is preferably performed in conjunction with a vehicle telematics system such as system 100 . Those skilled in the art should appreciate that the overall architecture, setup, operation and individual components of the system 100 are generally known in the art. Thus, the system description below provides only a brief overview of one such exemplary telematics system, but other systems and components not shown here may also support the methods disclosed herein.

[0020] The exemplary telematics system 100 includes a vehicle 102 for carrying one or more occupants or users and a wireless communication system 104 for providing two-way wireless communication with the vehicle 102 . Additionally, the system 100 may include a second communication system 106 for c...

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

A method of circumstantial speech recognition in a vehicle. A plurality of parameters associated with a plurality of vehicle functions are monitored as an indication of current vehicle circumstances. At least one vehicle function is identified as a candidate for user-intended ASR control based on user interaction with the vehicle. The identified vehicle function is then used to disambiguate between potential commands contained in speech received from the user.

Description

technical field [0001] The present invention relates to speech signal processing and, more particularly, to automatic speech recognition (ASR) for controlling vehicle functions. Background technique [0002] ASR technology enables computing devices equipped with microphones to translate speech, providing an alternative to traditional human input devices such as keyboards or keypads. A typical ASR system includes several basic components. A microphone and an acoustic interface receive utterance of words from the user and digitize the utterance into acoustic data. Acoustic preprocessors parse acoustic data into information-bearing acoustic features. The decoder uses the acoustic model to decode the acoustic features into utterance hypotheses. The decoder produces a confidence value for each hypothesis, reflecting how well each hypothesis phonetically matches a subword of each utterance, and selects the best hypothesis for each subword. Using a language model, the decoder c...

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): B60R16/037G10L15/00
CPCB60R16/0373
Owner GENERAL MOTORS LLC
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More