System and method for operating devices using voice commands
First Claim
1. A control component to enable operation of an electric device via voice commands, the control component comprising:
- a hybrid optical-and-acoustic sensor which comprises a self-mix interferometry unit, wherein the hybrid optical-and-acoustic sensor is (I) to capture audio uttered by a human speaker, and (II) to perform self-mix interferometry utilizing an optical feedback beam that is reflected back from said human speaker;
a voice detector to detect speech uttered within said audio, and to perform speech enhancement by utilizing said self-mix interferometry of the optical feedback beam that is reflected back from said human speaker during time-periods in which an optical beam hits a face of said human speaker;
an audio recorder to record audio captured by said hybrid optical-and-acoustic sensor, during a time-period in which speech is detected by said voice detector within said audio;
a wireless transmitter to wirelessly transmit to a remote server, over one or more wireless communication links, a message comprising;
(A) digital data reflecting the recorded audio;
(B) a Dictionary Identifier Code (DIC) to indicate a particular dictionary table that should be used for performing speech recognition on said recorded audio, out of multiple dictionary tables that correspond to multiple different electric devices that are voice-controllable;
a DIC selector module, (a) to determine that the electric device is currently operating within a particular operating mode; and
(b) to select a particular DIC value that corresponds to said particular operating mode, out of a plurality of DIC values stored within the electric device, wherein said particular DIC value indicates a limited-scope vocabulary dictionary that should be used by the remote server for speech recognition of the recorded audio when the electric device is operating in said particular operating mode;
a wireless transceiver to wirelessly receive from said remote server, over one or more wireless communication links, data representing a command code determined by said remote server based on speech recognition performed by said remote server on said recorded audio, wherein the command code represents a pre-defined command to the electric device to modify one or more operational parameters of the electric device; and
an operation control module to trigger one or more modifications to the operation of the electric device, based on the received command code.
1 Assignment
0 Petitions
Accused Products
Abstract
System and method for operating electric devices based on voice commands, as well as electric devices that can be controlled via voice commands. An electric device comprises an audio sensor to capture audio that contains speech; and a transmitter to transmit the captured audio to a remote server, together with a dictionary identifier that indicates to the remote server which particular dictionary or vocabulary-set to utilize for performing speech recognition on the recorded audio. The remote server performs speech recognition using the relevant dictionary table; and selects a command-code that is transmitted back to the electric device, to trigger an operational modification of the electric device.
23 Citations
12 Claims
-
1. A control component to enable operation of an electric device via voice commands, the control component comprising:
-
a hybrid optical-and-acoustic sensor which comprises a self-mix interferometry unit, wherein the hybrid optical-and-acoustic sensor is (I) to capture audio uttered by a human speaker, and (II) to perform self-mix interferometry utilizing an optical feedback beam that is reflected back from said human speaker; a voice detector to detect speech uttered within said audio, and to perform speech enhancement by utilizing said self-mix interferometry of the optical feedback beam that is reflected back from said human speaker during time-periods in which an optical beam hits a face of said human speaker; an audio recorder to record audio captured by said hybrid optical-and-acoustic sensor, during a time-period in which speech is detected by said voice detector within said audio; a wireless transmitter to wirelessly transmit to a remote server, over one or more wireless communication links, a message comprising;
(A) digital data reflecting the recorded audio;
(B) a Dictionary Identifier Code (DIC) to indicate a particular dictionary table that should be used for performing speech recognition on said recorded audio, out of multiple dictionary tables that correspond to multiple different electric devices that are voice-controllable;a DIC selector module, (a) to determine that the electric device is currently operating within a particular operating mode; and
(b) to select a particular DIC value that corresponds to said particular operating mode, out of a plurality of DIC values stored within the electric device, wherein said particular DIC value indicates a limited-scope vocabulary dictionary that should be used by the remote server for speech recognition of the recorded audio when the electric device is operating in said particular operating mode;a wireless transceiver to wirelessly receive from said remote server, over one or more wireless communication links, data representing a command code determined by said remote server based on speech recognition performed by said remote server on said recorded audio, wherein the command code represents a pre-defined command to the electric device to modify one or more operational parameters of the electric device; and an operation control module to trigger one or more modifications to the operation of the electric device, based on the received command code. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method to enable operation of an electric device via voice commands, the method comprising:
-
at a hybrid optical-and-acoustic sensor, which comprises a self-mix interferometry unit, performing;
(I) capturing audio uttered by a human speaker, and (II) performing self-mix interferometry utilizing an optical feedback beam that is reflected back from said human speaker;detecting that speech is uttered within said audio, and performing speech enhancement by utilizing said self-mix interferometry of the optical feedback beam that is reflected back from said human speaker during time-periods in which an optical beam hits a face of said human speaker; recording audio captured by said hybrid optical-and-acoustic sensor, during a time-period in which speech is detected within said audio; wirelessly transmitting to a remote server, over one or more wireless communication links, a message comprising;
(A) digital data reflecting the recorded audio;
(B) a Dictionary Identifier Code (DIC) to indicate a particular dictionary table that should be used for performing speech recognition on said recorded audio, out of multiple dictionary tables that correspond to multiple different electric devices that are voice-controllable;determining that the electric device is currently operating within a particular operating mode; and
selecting a particular DIC value that corresponds to said particular operating mode, out of a plurality of DIC values stored within the electric device;wherein said particular DIC value indicates a limited-scope vocabulary dictionary that should be used by the remote server for speech recognition of the recorded audio when the electric device is operating in said particular operating mode; wirelessly receiving from said remote server, over one or more wireless communication links, data representing a command code determined by said remote server based on speech recognition performed by said remote server on said recorded audio, wherein the command code represents a pre-defined command to the electric device to modify one or more operational parameters of the electric device; and triggering one or more modifications to the operation of the electric device, based on the received command code.
-
Specification