Acoustic impulse response simulation

• US 9,761,223 B2
• Filed: 10/13/2014
• Issued: 09/12/2017
• Est. Priority Date: 10/13/2014
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Blommer, Michael Alan, Amman, Scott Andrew, Richardson, Brigitte Frances Mora, Charette, Francois, Porter, Mark Edward, Puskorius, Gintaras Vincent, Cooprider, Anthony Dwayne
• Primary Examiner(s): Santiago Cordero, Marivelisse
• Assistant Examiner(s): BRINICH, STEPHEN M
• Application Number:
  US14/512,578
• Publication Number:
  US 20160104479A1
• Time in Patent Office: 1,065 Days
• Field of Search: 704 3, 704 7, 704246-255, 704257, 704200-201, 704225-226, 704231, 704243, 704270
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

At least one spoken utterance and a stored vehicle acoustic impulse response can be provided to a computing device. The computing device is programmed to provide at least one speech file based at least in part on the spoken utterance and the vehicle acoustic impulse response.

Claims

1. A system comprising a computing device that includes a processor and a memory, the memory storing instructions executable by the processor to:

perform a first convolution that includes convolving a spoken utterance with a second acoustic impulse response that is based on acoustic characteristics of a vehicle cabin;

receive output of a second convolution, of vehicle sounds retrieved from an electronic sound database with a first acoustic impulse response that is based on acoustic characteristics of a room, from a speaker in the room while recording the spoken utterance to generate output sounds that include the spoken utterance according to the first convolution; and

generate a speech file from the output sounds.

2. The system of claim 1, wherein a source for the spoken utterance includes a database of recorded utterances.

3. The system of claim 2, wherein the spoken utterance is provided as a digital sound file from the database of recorded utterances to the computing device.

4. The system of claim 1, further comprising a microphone for receiving the at least one spoken utterance, wherein the at least one spoken utterance is provided to a microphone and converted to a digital sound file that is provided to the computing device.

5. The system of claim 4, further comprising a head and torso simulator that is arranged to provide the at least one spoken utterance to the microphone.

6. The system of claim 1, further comprising the electronic sounds database that stores the vehicle sounds, the vehicle sounds being sounds that were recorded during operation of a vehicle.

7. The system of claim 6, further comprising a speaker for providing the recorded vehicle sounds.

8. The system of claim 1, comprising at least one equalizer arranged to receive and adjust the at least one spoken utterance.

9. The system of claim 1, the instructions further including instructions to, before generating the speech file from the output sounds, perform a third convolution that includes convolving the output sounds with a third acoustic impulse response that is based on acoustic characteristics of a microphone.

10. The system of claim 9, wherein the third acoustic impulse response is a stored hands-free microphone impulse response.

11. A method, comprising:

performing a first convolution that includes convolving a spoken utterance with a second acoustic impulse response that is based on acoustic characteristics of a vehicle cabin;

receiving output of a second convolution, of vehicle sounds retrieved from an electronic sound database with a first acoustic impulse response that is based on acoustic characteristics of a room, from a speaker in the room while recording the spoken utterance to generate output sounds that include the spoken utterance according to the first convolution; and

generating a speech file from the output sounds.

12. The method of claim 11, wherein a source for the spoken utterance includes a database of recorded utterances.

13. The method of claim 12, further comprising providing the spoken utterance as a digital sound file from the database of recorded utterances to the computing device.

14. The method of claim 11, further comprising using a microphone for receiving the at least one spoken utterance, wherein the at least one spoken utterance is provided to a microphone and converted to a digital sound file that is provided to the computing device.

15. The method of claim 14, further comprising providing a head and torso simulator that is arranged to provide the at least one spoken utterance to the microphone.

16. The method of claim 11, wherein the vehicle sounds were recorded during operation of a vehicle.

17. The method of claim 16, further comprising providing the recorded vehicle sounds from a speaker.

18. The method of claim 11, further comprising, before generating the speech files from the output sounds, performing a third convolution that includes convolving the output sounds with a third acoustic impulse response that is based on acoustic characteristics of a microphone.

19. The method of claim 18, wherein the third acoustic impulse response is a stored hands-free microphone impulse response.

20. The method of claim 11, further comprising providing at least one equalizer arranged to receive and adjust the at least one spoken utterance.