System and method for transmitting voice input from a remote location over a wireless data channel
First Claim
Patent Images
1. A voice communication method comprising:
- receiving an acoustic analog signal at a user system directly from a user;
converting the analog signal to a digital signal;
canceling noise from the digital signal to form a processed digital signal;
detecting user speech in the processed digital signal by evaluating two or more of noise cancellation, echo-cancellation or end-pointing, wherein the detected user speech is in a format capable of being outputted over a speaker;
sending the detected user speech to a server over a network, and performing speech recognition processing of the sent detected user speech at the server.
22 Assignments
0 Petitions
Accused Products
Abstract
A system and method for improving voice recognition processing at a server system that receives voice input from a remotely located user system. The user system includes a microphone, a processor that performs front-end voice recognition processing of the received user voice input, and a communication component configured to send the front-end processed user voice input to a destination wirelessly over a network. The server system includes a communication component configured to receive the sent front-end processed user voice input, and a processor configured to complete voice recognition processing of the sent front-end processed user voice input.
50 Citations
25 Claims
-
1. A voice communication method comprising:
-
receiving an acoustic analog signal at a user system directly from a user;
converting the analog signal to a digital signal;
canceling noise from the digital signal to form a processed digital signal;
detecting user speech in the processed digital signal by evaluating two or more of noise cancellation, echo-cancellation or end-pointing, wherein the detected user speech is in a format capable of being outputted over a speaker;
sending the detected user speech to a server over a network, and performing speech recognition processing of the sent detected user speech at the server. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A voice communication method comprising:
-
receiving an acoustic analog signal at a user system directly from a user;
converting the analog signal to a digital signal;
canceling noise from the digital signal to form a processed digital signal;
detecting user speech in the processed digital signal by evaluating two or more of noise cancellation, echo-cancellation or end-pointing, wherein the detected user speech is in a format capable of being outputted over a speaker;
sending the detected user speech to a server over a network;
performing speech recognition processing of the detected user speech at the server, and performing a function at the server based on the performed speech recognition processing.
-
-
10. A voice communication system comprising:
a user system comprising;
a microphone configured to receive user acoustic analog signals;
a processor configured to convert the analog signals to digital signals and process the digital signals based on two or more of noise cancellation, echo-cancellation or end-pointing to form a processed voice signal, wherein the processed voice signal is in a format capable of being outputted over a speaker; and
a communication component configured to send the processed voice signal to a destination over a network; and
a server system coupled to the network, the server comprising;
a communication component configured to receive the sent processed voice signal; and
a processor configured to perform speech recognition processing of the sent processed voice signal. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17)
-
18. A voice communication system comprising:
-
a means for receiving user acoustic analog signals at a user system directly by a user;
a means for converting the analog signals to digital signals;
a means for processing the digital signals at the user system based on two or more of noise cancellation, echo-cancellation or end-pointing to form a processed voice signal, wherein the processed voice signal is in a format capable of being outputted over a speaker;
a means for sending the processed voice signal to a server over a network; and
a means for performing speech recognition processing of the sent processed voice signal at the server. - View Dependent Claims (19, 20, 21, 22, 23, 24, 25)
-
Specification