Robust voice browser system and voice activated device controller
DCFirst Claim
Patent Images
1. A method for controlling at least one remote system by uttering speech commands into a voice enabled device, said method comprising the steps of:
- providing a computer operatively connected to the internet, said computer further being operatively connected to at least one speaker-independent speech recognition engine and to at least one speech synthesis engine;
providing a voice enabled device operatively connected to said computer, said voice enabled device configured to receive speech commands from users;
providing at least one instruction set stored in a database operatively connected to said computer, said instruction set comprising;
at least one internet address, said at least one internet address identifying the location of said at least one remote system, said at least one remote system configured to execute at least one pre-selected function; and
said at least one pre-selected function;
providing a speech command to said speaker-independent speech recognition engine, said speech command corresponding to said instruction set;
said speaker-independent speech recognition engine assigning said speech command to a recognition grammar, said speech command and said recognition grammar corresponding to said instruction set;
transmitting said speech command to said speaker-independent speech recognition engine;
said speaker-independent speech recognition engine receiving said speech command and selecting the corresponding recognition grammar upon receiving said speech command;
said computer retrieving said instruction set corresponding to said recognition grammar selected by said speaker-independent speech recognition engine;
said computer accessing said at least one remote system identified by said instruction set to prompt said at least one remote system to execute said at least one pre-selected function; and
said at least one remote system executing said at least one pre-selected function.
4 Assignments
Litigations
2 Petitions
Accused Products
Abstract
The present invention relates to a system for controlling at least one remote system operatively connected to the Internet. The system includes a computer operatively connected to the Internet and a database operatively connected to the computer, the database storing an instruction set used to identify the remote system. In response to a speech command received from a user, the computer is configured to access the remote system to prompt the remote system to execute at least one pre-selected function.
-
Citations
16 Claims
-
1. A method for controlling at least one remote system by uttering speech commands into a voice enabled device, said method comprising the steps of:
-
providing a computer operatively connected to the internet, said computer further being operatively connected to at least one speaker-independent speech recognition engine and to at least one speech synthesis engine; providing a voice enabled device operatively connected to said computer, said voice enabled device configured to receive speech commands from users; providing at least one instruction set stored in a database operatively connected to said computer, said instruction set comprising; at least one internet address, said at least one internet address identifying the location of said at least one remote system, said at least one remote system configured to execute at least one pre-selected function; and said at least one pre-selected function; providing a speech command to said speaker-independent speech recognition engine, said speech command corresponding to said instruction set; said speaker-independent speech recognition engine assigning said speech command to a recognition grammar, said speech command and said recognition grammar corresponding to said instruction set; transmitting said speech command to said speaker-independent speech recognition engine; said speaker-independent speech recognition engine receiving said speech command and selecting the corresponding recognition grammar upon receiving said speech command; said computer retrieving said instruction set corresponding to said recognition grammar selected by said speaker-independent speech recognition engine; said computer accessing said at least one remote system identified by said instruction set to prompt said at least one remote system to execute said at least one pre-selected function; and said at least one remote system executing said at least one pre-selected function. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system for controlling at least one remote system operatively connected to the internet by uttering speech commands into a phone, said system comprising:
-
a computer, said computer operatively connected to the internet and to at least one phone; at least one speaker-independent speech recognition engine, said speaker-independent speech recognition engine operatively connected to said computer; at least one speech synthesis engine, said speech synthesis engine operatively connected to said computer; a database, said database operatively connected to said computer; at least one instruction set stored in said database, said instruction set comprising; at least one internet address, said at least one internet address identifying the location of said at least one remote system, said at least one remote system configured to execute at least one pre-selected function; and said at least one pre-selected function; at least one recognition grammar stored in said database, each said recognition grammar corresponding to each said instruction set and corresponding to a speech command; said speaker-independent speech recognition engine configured to receive from users via said phone a speech command and to select the corresponding recognition grammar upon receiving said speech command; said computer configured to retrieve said instruction set corresponding to said recognition grammar selected by said speaker-independent speech recognition device; said computer further configured to access said at least one remote system identified by said instruction set to prompt said at least one remote system to execute said at least one pre-selected function; and said at least one remote system configured to execute said at least one pre-selected function. - View Dependent Claims (10, 11, 12, 13, 14, 15)
-
-
16. A method for controlling at least one remote system by uttering speech commands into a voice enabled device, said at least one remote system comprising an outdoor lighting system, an indoor lighting system, a security system, a heating system, or an air conditioning system, said method comprising the steps of:
-
providing a computer operatively connected to the internet, said computer further being operatively connected to at least one speaker-independent speech recognition engine and to at least one speech synthesis engine; providing a voice enabled device operatively connected to said computer, said voice enabled device configured to receive speech commands from users; providing at least one instruction set stored in a database operatively connected to said computer, said instruction set comprising; at least one internet address, said at least one internet address-identifying the location of said at least one remote system, said at least one remote system configured to execute at least one pre-selected function; and said at least one pre-selected function, said pre-selected function comprising turning the outdoor lighting on, turning the outdoor lighting off, dimming the outdoor lighting, turning the indoor lighting on, turning the indoor lighting off, dimming the indoor lighting, arming the security system, disarming the security system, turning the heating system on, turning the heating system off adjusting the heating system temperature, turning the air conditioning on, turning the air conditioning off, or adjusting the air conditioning temperature; providing a speech command to said speaker-independent speech recognition engine, said speech command corresponding to said instruction set; said speaker-independent speech recognition engine assigning said speech command to a recognition grammar, said speech command and said recognition grammar corresponding to said instruction set; transmitting said speech command to said speaker-independent speech recognition engine; said speaker-independent speech recognition engine receiving said speech command and selecting the corresponding recognition grammar upon receiving said speech command; said computer retrieving said instruction set corresponding to said recognition grammar selected by said speaker-independent speech recognition engine; said computer accessing said at least one remote system-identified by said instruction set to prompt said at least one remote system to execute said at least one pre-selected function; said at least one remote system executing said at least one pre-selected function; and said computer periodically polling said at least one remote system to determine whether said at least one remote system is operational or out of service.
-
Specification