Distributed voice recognition system
First Claim
1. A distributed voice recognition system, comprising:
- a digital signal processor configured to receive digitized speech samples and extract therefrom a plurality of parameters, the digital signal processor including a vocoder configured to generate diagnostic data and vocoder packets;
a storage medium containing a plurality of speech templates; and
a processor coupled to the storage medium and to the digital signal processor, the processor being configured to receive the plurality of parameters and the vocoder packets from the digital signal processor and compare the plurality of parameters with the speech templates.
1 Assignment
0 Petitions
Accused Products
Abstract
A distributed voice recognition system includes a digital signal processor (DSP), a nonvolatile storage medium, and a microprocessor. The DSP is configured to extract parameters from digitized input speech samples and provide the extracted parameters to the microprocessor. The nonvolatile storage medium contains a database of speech templates. The microprocessor is configured to read the contents of the nonvolatile storage medium, compare the parameters with the contents, and select a speech template based upon the comparison. The nonvolatile storage medium may be a flash memory. The DSP may be a vocoder. If the DSP is a vocoder, the parameters may be diagnostic data generated by the vocoder. The distributed voice recognition system may reside on an application specific integrated circuit (ASIC).
106 Citations
14 Claims
-
1. A distributed voice recognition system, comprising:
-
a digital signal processor configured to receive digitized speech samples and extract therefrom a plurality of parameters, the digital signal processor including a vocoder configured to generate diagnostic data and vocoder packets;
a storage medium containing a plurality of speech templates; and
a processor coupled to the storage medium and to the digital signal processor, the processor being configured to receive the plurality of parameters and the vocoder packets from the digital signal processor and compare the plurality of parameters with the speech templates. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A method of distributing voice recognition processing, comprising the steps of:
-
in a digital signal processor, extracting a plurality of parameters from a plurality of digitized speech samples with a vocoder configured to generate diagnostic data and vocoder packets;
providing the plurality of parameters and the vocoder packets to a microprocessor; and
in the microprocessor, comparing the plurality of parameters to a plurality of speech templates. - View Dependent Claims (7, 8)
-
-
9. A distributed voice recognition system, comprising:
-
means for extracting a plurality of parameters from a plurality of digitized speech samples, the means for extracting comprising means for generating vocoder packets and diagnostic data;
means for storing a plurality of speech templates; and
means for receiving the plurality of parameters and the vocoder packets from the means for extracting and comparing the plurality of parameters with the plurality of speech templates. - View Dependent Claims (10, 11, 12, 13, 14)
-
Specification