Speech recognition control device

• US 9,830,906 B2
• Filed: 04/08/2014
• Issued: 11/28/2017
• Est. Priority Date: 04/09/2013
• Status: Active Grant

• Current Assignee: Kojima Industries Corporation
• Original Assignee: Kojima Industries Corporation
• Inventors: Inose, Takashi, Nakamura, Shinobu
• Primary Examiner(s): Cordero, Marivelisse Santiago
• Assistant Examiner(s): Harris, Keara
• Application Number:
  US14/247,782
• Publication Number:
  US 20140303969A1
• Time in Patent Office: 1,330 Days
• Field of Search: None
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems

Abstract

A speech recognition control device has a plurality of microphones placed at different positions, a speech transmission control unit, and a speech recognition execution control unit. The speech transmission control unit stores data based on the speeches which are input from the microphones and time data related to ranks among the microphones, assigns ranks to the plurality of microphones using the time data based on a preset condition, and transmits a speech data signal corresponding to the microphone to the speech recognition execution control unit in the order of the ranks. The speech recognition execution control unit executes the speech recognition process according to the order of the speech data signals transmitted from the speech transmission control unit.

Claims

1. An on-vehicle speech recognition control device having a speech recognition execution control unit adapted to execute a speech recognition process to recognize that an input speech data signal is an execution command and adapted to execute the execution command, the speech recognition control device comprising:

a plurality of microphones placed at different positions located at peripheral portions of a plurality of seats, respectively, within a vehicle; and

a speech transmission control unit adapted to store data based on a speech which is input from each of the microphones and data related to ranks among the microphones and indicating an order of completion of the speeches, the speech transmission control unit being further adapted to assign ranks to the plurality of microphones based on the data indicating the order of completion of the speeches in the order from an earlier completion time of the speech, when speeches are simultaneously input from the plurality of microphones, the speech transmission control unit being further adapted to transmit speech data signals corresponding to the microphones to the speech recognition execution control unit in an order of the ranks, wherein

the speech recognition execution control unit is adapted to execute the speech recognition process according to an order of the speech data signals transmitted from the speech transmission control unit.

2. The on-vehicle speech recognition control device according to claim 1, wherein the speech transmission control unit uses at least a first microphone of the plurality of microphones as a noise canceller to remove a waveform corresponding to a first time waveform of a speech obtained through the first microphone from a second time waveform of a speech obtained through a second microphone of the plurality of microphones.

3. The on-vehicle speech recognition control device according to claim 2, wherein the speech transmission control unit calculates a ratio W2/W1, wherein W2 is a maximum amplitude of the second time waveform and W1 is a maximum amplitude of the first time waveform at a predetermined time, and removes, from the second time waveform, a waveform obtained by reducing a level of the first time waveform using the calculated ratio as the waveform corresponding to the first time waveform.

4. The on-vehicle speech recognition control device according to claim 2, wherein the speech transmission control unit determines a speech time waveform that is to be used as a noise canceller from among time waveforms of speeches obtained through the plurality of microphones, based on at least the promptness of the reaching time of the speech to the speech transmission control unit.