Dynamic selection of appropriate far-field signal separation algorithms
US-2024257825-A1 · Aug 1, 2024 · US
US9406310B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9406310-B2 |
| Application number | US-201213345531-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jan 6, 2012 |
| Priority date | Jan 6, 2012 |
| Publication date | Aug 2, 2016 |
| Grant date | Aug 2, 2016 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A vehicle voice interface system calibration method comprising electronically convolving voice command data with voice impulse response data, electronically convolving audio system output data with feedback impulse response data, and calibrating the vehicle voice interface system. The voice command data is electronically convolved with voice impulse response data representing a voice acoustic signal path between an artificial mouth simulator and a first microphone, to simulate a voice acoustic transfer function pertaining to the passenger compartment. The audio system output data is convolved with feedback impulse response data representing a feedback acoustic signal path between a vehicle audio system output and a second microphone, to simulate a feedback acoustic transfer function pertaining to the passenger compartment. The voice interface system is calibrated to recognize voice commands represented by the voice command data based on the simulated voice and feedback acoustic transfer functions.
Opening claim text (preview).
What is claimed is: 1. A vehicle voice interface system calibration method comprising: electronically convolving voice command data with voice impulse response data representing a voice acoustic signal path between an artificial mouth simulator present in a passenger compartment of a vehicle and a first microphone present in the passenger compartment, to simulate a voice acoustic transfer function pertaining to the passenger compartment of the vehicle; electronically convolving audio system output data with feedback impulse response data representing a feedback acoustic signal path between a vehicle audio system output and a second microphone present in the passenger compartment, to simulate a feedback acoustic transfer function pertaining to the passenger compartment of the vehicle; combining a voice electrical signal representing the simulated voice acoustic transfer function and a feedback electrical signal representing the simulated feedback acoustic transfer function into a combined electrical signal; providing the combined electrical signal to a microphone electrical input of the vehicle voice interface system; and calibrating the vehicle voice interface system to recognize voice commands represented by the voice command data based on the combined electrical input signal. 2. The vehicle voice interface system calibration method of claim 1 , further comprising obtaining a baseline data including the voice impulse response data and the feedback impulse response data by: positioning the artificial mouth simulator in the passenger compartment of the vehicle; operating the mouth simulator to output a first reference audio signal; operating the vehicle audio system output to output a second reference audio signal; capturing the voice impulse response data representing the acoustic signal path between the mouth simulator and the first microphone; and capturing the feedback impulse response data representing the acoustic signal path between the vehicle audio system output and the second microphone. 3. The method according to claim 2 , wherein the obtaining baseline data further includes positioning an artificial ear simulator in the passenger compartment of the vehicle that includes the second microphone. 4. The method according to claim 2 , wherein the first and second microphones are a microphone input of the vehicle voice interface system; the capturing of the voice impulse response data obtains the voice impulse response data representing the voice acoustic signal path between the artificial mouth simulator and the microphone input of the vehicle voice interface system; and the capturing of the feedback impulse response data obtains the feedback impulse response data representing the feedback acoustic signal path between the vehicle audio system output and the microphone input of the vehicle voice interface system. 5. The method according to claim 2 , wherein the vehicle audio system output includes a left speaker and a right speaker; and the obtaining of the feedback impulse response data includes obtaining first feedback impulse response data representing a feedback acoustic signal path between the left speaker and the second microphone and obtaining second feedback impulse response data representing a feedback acoustic signal path between the right speaker and the second microphone, the feedback impulse response data including the first and second feedback impulse response data. 6. The method according to claim 1 , wherein the combining further comprises combining the voice electrical signal, the feedback electrical signal and a noise electrical signal representing noise associated with the vehicle into the combined electrical signal that is provided to the microphone electrical input of the vehicle voice interface system and used during the calibrating to calibrate the vehicle voice interface system. 7. The method according to claim 6 , further comprising converting the voice electrical signal representing the simulated voice acoustic transfer function and the feedback electrical signal representing the simulated feedback acoustic transfer function from digital electrical signals to an analog electrical simulated voice acoustic transfer function signal and an analog electrical simulated feedback acoustic transfer function signal, respectively; and wherein the noise electrical signal representing noise is an analog electrical noise signal; and the combining includes combining the analog electrical noise signal with the analog electrical simulated voice acoustic transfer function signal and the analog electrical simulated feedback acoustic transfer function signal to provide an analog combined electrical signal to the microphone electrical input of the vehicle voice interface system. 8. The method according to claim 1 , further comprising operating a computer to perform the electronically convolving of the voice command data with the voice impulse response data and the electronically convolving of audio system output data with the feedback impulse response data; operating the computer to perform the combining of the voice electrical signal and the feedback electrical signal into the combined electrical signal; and operating the computer to perform the providing of the combined electrical input signal to the microphone electrical input of the vehicle voice interface system. 9. The method according to claim 8 , further comprising operating a noise mixing device outside of the computer to combine the combined electrical signal and a noise electrical signal representing noise associated with the vehicle into a second combined electrical signal; and wherein the calibrating includes calibrating the vehicle voice interface system based on the second combined electrical signal. 10. The method according to claim 1 , wherein the vehicle voice interface system includes a voice recognition system; and the calibrating includes calibrating the voice recognition system to recognize the voice commands represented by the voice command data based on the simulated voice acoustic transfer function and the simulated feedback acoustic transfer function. 11. The method according to claim 1 , wherein the vehicle voice interface system includes a mobile hands-free interface device; and the calibrating includes calibrating the mobile hands-free interface device to recognize the voice commands represented by the voice command data based on the simulated voice acoustic transfer function and the simulated feedback acoustic transfer function. 12. The method according to claim 1 , wherein the calibrating of the vehicle voice interface system includes changing at least one of a volume, a noise cancellation parameter and an echo cancellation parameter of the vehicle voice interface system to calibrate the vehicle voice interface system to recognize the voice commands represented by the voice command data based on the simulated voice acoustic transfer function and the simulated feedback acoustic transfer function. 13. A vehicle voice interface system calibration method comprising: obtaining a baseline data including a voice impulse response data and a feedback impulse response by: positioning an artificial mouth simulator in a passenger compartment of a vehicle; operating the mouth simulator to output a first reference audio signal; operating a vehicle audio system output to output a second reference audio signal; capturing the voice impulse response data representing the acoustic signal path between the mouth simulator and a first microphone; and capturing the feedback impulse response data representing the acoustic signal path be
the noise being echo, reverberation of the speech · CPC title
characterised by the method used for estimating noise · CPC title
Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title
characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques · CPC title
using speech input, e.g. using speech recognition · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.