Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
2000-10-26
2004-12-14
Dorvil, Richemond (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
C704S221000, C704S213000, C704S244000, C704S230000, C704S274000, C712S038000, C712S205000, C712S213000, C712S205000
Reexamination Certificate
active
06832194
ABSTRACT:
BACKGROUND OF THE INVENTION
The field of the present invention is integrated circuits for implementing audio recognition. More particularly, the present invention includes an apparatus and method of providing an audio recognition peripheral system allowing for a highly efficient implementation of an audio recognition process.
Audio recognition systems are widely used for providing computers and other electronic systems with the ability to receive audio input signals and perform operations in response to the particular characteristics of the audio input signal. One common application of audio recognition is speech recognition, for example. Using a speech recognition system, a computer or other electronic system may receive an audio input signal corresponding to speech and respond to the input signal in accordance with the specific speech that was received. For example, a user may provide spoken commands to a computer and using a speech recognition algorithm the computer may execute different functions in response different commands.
However, audio recognition systems are problematic to realize because they typically require large amounts of data processing to implement. For example, in one prior art implementation, an audio signal is digitized and provided as an input to a microprocessor. The microprocessor performs the speech recognition using software algorithms that operate on the digitized audio signal. This approach has the disadvantage of consuming large amounts resources and/or processor time in the microprocessor, thereby slowing down the performance of the overall system.
In another prior art implementation of an audio recognition system, an application specific audio recognition integrated circuit is used that incorporates a dedicated microprocessor with special hardware and software for performing the audio recognition operations. However, application specific audio recognition systems have the disadvantage of increasing the costs of the overall system. Moreover, application specific audio recognition systems are difficult to integrate into larger systems because of compatibility issues between the operating characteristics of the different devices in the system. Additionally, an application specific audio recognition integrated circuit will often be integrated into an electronic system controlled by a main processor. However, as the applications on the main processor are modified, additional modifications and adaptations on the application specific audio recognition integrated circuit may be required to conform to software changes in the main processor. Such modifications can be difficult, costly, and time consuming, and can make the overall electronic system costly and inflexible. Finally, application specific audio recognition systems typically have their own programming environments that users must learn in order to implement audio recognition functionality. Therefore, design cycles are increased in the development of new systems with a corresponding increase in cost.
Therefore, what is needed is an audio recognition system that allows users to efficiently implement audio recognition functionality into larger systems at reduced costs with both ease and flexibility of use.
SUMMARY OF THE INVENTION
Embodiments of the present invention solve the problems described above with respect to previously known systems and methods for implementing audio recognition. Specifically, the present invention provides an audio recognition peripheral and audio recognition peripheral system. The present invention allows system designers to easily add audio recognition functionality into a system by simply adding a low cost audio recognition peripheral to operate in conjunction with a processor.
In one embodiment the present invention includes an audio recognition peripheral system comprising a first integrated circuit having a programmable processing unit, the programmable processing unit loading an audio recognition algorithm to perform an audio recognition operation, and a second integrated circuit having a feature extractor coupled to the first integrated circuit, the second integrated circuit receiving an audio signal and extracting audio recognition features from the audio signal to produce feature extraction data, wherein the programmable processing unit receives the feature extraction data and executes the audio recognition algorithm on the feature extraction data.
In another embodiment, the second integrated circuit of the audio recognition peripheral system includes an interface controller coupled to the feature extractor and to the first integrated circuit, the interface controller operating in response to control signals received from the first integrated circuit.
In another embodiment, the second integrated circuit of the audio recognition peripheral system includes a vector processor coupled to the first integrated circuit, wherein interface information is received by the interface controller and includes information for configuring the vector processor to perform a specified operation during execution of the audio recognition algorithm by the programmable processing unit.
In one embodiment, the present invention includes an audio recognition peripheral on a single integrated circuit comprising a feature extractor, having an audio input for receiving an audio signal, the feature extractor extracting audio recognition features from the audio signal to produce feature extraction data, and an interface controller coupled to the feature extractor, the interface controller having an interface input for receiving external control signals and interface information, wherein the control signals and interface information configure the feature extractor to operate in accordance with an external audio recognition algorithm.
In another embodiment, when the audio recognition peripheral is in an extraction mode a filter unit receives an audio signal to generate feature extraction data, and when the audio recognition peripheral is in a synthesis mode the filter unit receives an excitation signal to generate audio information.
In another embodiment, the audio recognition peripheral further comprises a synthesizer for receiving digital audio information and producing an external analog audio output signal.
In another embodiment, the audio recognition peripheral further comprises a vector processor coupled to the interface controller. In yet another embodiment, the audio recognition peripheral further comprises a memory coupled to the vector processor.
In one embodiment, the present invention includes an audio recognition method comprising loading an audio recognition algorithm in a first integrated circuit, the first integrated circuit having a programmable processing unit, transmitting control signals and interface information from the first integrated circuit to a second integrated circuit having a feature extractor, and in accordance therewith, configuring the second integrated circuit to extract audio recognition features, receiving an audio signal in the feature extractor of the second integrated circuit, extracting audio recognition features from the audio signal to produce feature extraction data, transmitting the feature extraction data from the second integrated circuit to the first integrated circuit, and executing the audio recognition algorithm on the feature extraction data in the first integrated circuit.
In one embodiment, the present invention includes a method of processing an audio signal on a single integrated circuit for audio recognition comprising receiving external control signals and interface information in a interface controller corresponding to the external execution of an audio recognition algorithm, and in accordance therewith, configuring a feature extractor, receiving the audio signal in the feature extractor, extracting audio recognition features from the audio signal to produce feature extraction data, and transmitting the feature extraction data external to the integrated circuit.
These and other embodiments of the present invention, as well as its advant
Mozer Forrest S.
Savoie Robert E.
Teasley William T.
Dorvil Richemond
Fountainhead Law Group
Han Qi
Sensory, Incorporated
Walsh Chad R.
LandOfFree
Audio recognition peripheral system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Audio recognition peripheral system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Audio recognition peripheral system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3318034