Apparatus and method for recognizing voice

• US 9,530,406 B2
• Filed: 04/03/2014
• Issued: 12/27/2016
• Est. Priority Date: 11/25/2013
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Inventors: Oh, Seok Min
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): KIM, JONATHAN C
• Application Number:
  US14/244,447
• Publication Number:
  US 20150149164A1
• Time in Patent Office: 999 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: B60N 2/0272 using sensors or detectors for detecting the position of seat parts
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 2021/02166 Microphone arrays; Beamforming
• CPC Class Codes: H04R 1/326 for microphones H04R1/34 and H04R1/40 take precedence
• CPC Class Codes: H04R 1/406 microphones
• CPC Class Codes: H04R 2201/401 2D or 3D arrays of transducers
• CPC Class Codes: H04R 2201/403 Linear arrays of transducers
• CPC Class Codes: H04R 2430/20 Processing of the output signals of the acoustic transducers of an array for obtaining a desired directivity characteristic H04R2203/12 takes precedence
• CPC Class Codes: H04R 2499/13 Acoustic transducers and sound field adaptation in vehicles
• CPC Class Codes: H04R 3/005 for combining the signals of two or more microphones specially adapted for hearing aids H04R25/407

Abstract

An apparatus and a method for recognizing a voice include a plurality of array microphones configured to have at least one microphone, and a seat controller configured to check a position of a seat provided in a vehicle. A microphone controller is configured to set a beam forming region based on the checked position of the seat and controls an array microphone so as to obtain sound source data from the set beam forming region.

Claims

1. An apparatus for recognizing a voice, the apparatus comprising:

a plurality of array microphones configured to have at least one microphone;

a seat controller configured to check a position of a seat provided in a vehicle; and

a microphone controller configured to set a beam forming region based on the checked position of the seat and control the array microphones so as to obtain sound source data from the set beam forming region,

wherein the microphone controller recognizes a total movement distance of the seat as a total beam forming angle of the array microphones,

wherein the microphone controller divides the total movement distance of the seat equally into a plurality of sections and divides the total beam forming angle of the array microphones equally into a plurality of sections according to the divided sections to thereby form first beam forming sections,

wherein the microphone controller sets a section corresponding to the seat position among the first beam forming sections as a first beam forming region,

wherein the microphone controller divides the first beam forming region into a plurality of sections to thereby generate a plurality of second beam forming sections, and

wherein the microphone controller compares each of the plurality of second beam forming sections and sets a section from which a signal having the largest strength is obtained among signals of sound source data obtained from a first array microphone and a second array microphone as a second beam forming region.

2. The apparatus according to claim 1, further comprising a voice recognizer extracting voice data from the sound source data obtained from the second beam forming region.

4. The apparatus according to claim 1, further comprising:

a seat switch generating a signal for changing the seat position and providing the signal to the seat controller; and

a seat driver configured to change the seat position based on a control of the seat controller.

3. A method for recognizing a voice, the method comprising:

activating a plurality of array microphones when a signal for entering a voice recognition mode is received from the outside;

checking a position of a seat provided in a vehicle;

setting a beam forming region based on the checked position of the seat;

obtaining sound source data from the beam forming region; and

extracting voice data from the obtained sound source data,

wherein a total movement distance of the seat is recognized as a total beam forming angle of the array microphones,

wherein the step of checking the seat position includes dividing the total movement distance of the seat equally into sections and checking whether the seat is positioned at any position of the divided sections,

wherein the step of setting the beam forming region includes;

forming first beam forming sections by dividing the total beam forming angle of the array microphones to be equal to the sections obtained by dividing the total movement distance; and

setting a section corresponding to the seat position among the first beam forming sections as a first beam forming region,

wherein a second beam forming region is selected after the section corresponding the seat position among the first beam forming sections are set as a first bean forming region,

wherein the step of selecting the second beam forming region includes;

dividing the first beam forming region into a plurality of sections;

obtaining, by a first array microphone and a second array microphone, sound source data of different sections from a plurality of second beam forming sections;

comparing strengths of sound source data signals obtained from the first array microphone and the second array microphone; and

selecting a section from which a signal having the largest strength is obtained as the second beam forming region according to the comparison result after comparing each of the plurality of second beam forming sections.