Unified microphone pre-processing system and method
First Claim
1. A processor implemented method for using a single set of spatially disparate microphones for plurality of audio applications, the method comprising:
- receiving signals from the microphones;
processing the received signals to produce one or more processed-signals;
providing the processed-signals to the plurality of audio applications, the plurality of audio applications comprising at least;
an active noise cancellation application, and one of;
a telephony application and an automatic speech recognition application; and
outputting inverted noise signals via one or more speakers, wherein the inverted noise signals are generated by the active noise cancellation application;
further wherein the processing comprises;
performing enhancement to the received signals, the enhancement configured for acoustic echo cancellation;
performing noise reduction and residual echo reduction, both by;
steering at least one of multiple reception beams to a speaker'"'"'s mouth,using signal enhancement technique, andusing signal reconstruction technique;
performing a speech recognition enhancement pre-processing on the received signals, wherein the speech recognition enhancement pre-processing is configured to optimize a metric of at least one of;
Mel cepstrum distance or word recognition rate; and
performing sound pressure measurements near a head of one or more occupants.
3 Assignments
0 Petitions
Accused Products
Abstract
A unified microphone pre-processing system includes a plurality of microphones arranged within a vehicle passenger compartment, a processing circuit or system configured to receive signals from one or more of the plurality of microphones, and the processing circuit configured to enhance the received signals for use by at least two of a telephony processing application, an automatic speech recognition processing application, and a noise cancellation processing application. The method includes receiving signals from one or more of a plurality of microphones arranged within a vehicle passenger compartment, and enhancing the received signals for use by at least two of a telephony processing application, an automatic speech recognition processing application, and a noise cancellation processing application. A computer readable medium containing executable instructions to cause a processor to perform a method in accordance with an embodiment of the invention is also described.
42 Citations
17 Claims
-
1. A processor implemented method for using a single set of spatially disparate microphones for plurality of audio applications, the method comprising:
-
receiving signals from the microphones; processing the received signals to produce one or more processed-signals; providing the processed-signals to the plurality of audio applications, the plurality of audio applications comprising at least;
an active noise cancellation application, and one of;
a telephony application and an automatic speech recognition application; andoutputting inverted noise signals via one or more speakers, wherein the inverted noise signals are generated by the active noise cancellation application; further wherein the processing comprises; performing enhancement to the received signals, the enhancement configured for acoustic echo cancellation; performing noise reduction and residual echo reduction, both by; steering at least one of multiple reception beams to a speaker'"'"'s mouth, using signal enhancement technique, and using signal reconstruction technique; performing a speech recognition enhancement pre-processing on the received signals, wherein the speech recognition enhancement pre-processing is configured to optimize a metric of at least one of;
Mel cepstrum distance or word recognition rate; andperforming sound pressure measurements near a head of one or more occupants. - View Dependent Claims (2)
-
-
3. A unified microphone pre-processing system comprising:
-
a plurality of microphones arranged within a vehicle passenger-compartment; one or more loudspeakers arranged within the vehicle passenger-compartment; a memory unit comprising; an active noise cancellation processing application (ANCPA) configured to output inverted noise signals via at least one of the loudspeakers, and at least one of;
telephony processing application and automatic speech recognition processing application; anda processor configured for; receiving signals from the plurality of microphones, performing enhancement to the received signals, the enhancement configured for acoustic echo cancellation, performing noise reduction and residual echo reduction, both by; steering at least one of multiple reception beams to a speaker'"'"'s mouth, using signal enhancement technique, and using signal reconstruction technique, performing a speech recognition enhancement pre-processing on the received signals, wherein the speech recognition enhancement pre-processing is configured to optimize a metric of at least one of;
Mel cepstrum distance or word recognition rate, andperforming sound pressure measurements near a head of one or more occupants; generating one or more enhanced-signals; and outputting the inverted noise signals via the one or more speakers; wherein; at least one of the enhanced-signals is configured to serve as input to the ANCPA, and at least one of the enhanced-signals is configured to serve as input to at least one of;
the telephony processing application and the automatic speech recognition processing application. - View Dependent Claims (4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A processor implemented method for unified microphone pre-processing, the method comprising:
-
receiving signals from a plurality of microphones, wherein the microphones are arranged within a vehicle passenger-compartment; pre-processing the received signals, wherein the pre-processing comprises; performing enhancement to the received signals, the enhancement configured for acoustic echo cancellation, performing noise reduction and residual echo reduction, both by; steering at least one of multiple reception beams to a speaker'"'"'s mouth, using signal enhancement technique, and using signal reconstruction technique, performing a speech recognition enhancement pre-processing on the received signals, wherein the speech recognition enhancement pre-processing is configured to optimize a metric of at least one of;
Mel cepstrum distance or word recognition rate, andperforming sound pressure measurements near a head of one or more occupants; generating one or more enhanced-signals, wherein; at least one of the enhanced-signals is configured for serving as input to an active noise cancellation processing application (ANCPA) stored in a memory, and at least one of the enhanced-signals is configured for serving as input to at least one of;
telephony processing application stored in a memory and automatic speech recognition processing application stored in a memory; andoutputting inverted noise signals via one or more loudspeakers arranged within the vehicle passenger-compartment, wherein the inverted noise signals are generated by the ANCPA. - View Dependent Claims (13, 14, 15, 16, 17)
-
Specification