Client-server speech recognition by encoding speech as packets transmitted via the internet
First Claim
Patent Images
1. A method comprising:
- coupling a first client to a server through the Internet, wherein the first client comprises a capability to receive audio speech from a user,at the first client after receiving the audio speech, the first client encodes the received audio speech, andafter encoding the received audio speech, the first client transmits packets of encoded audio speech along with a first value to the server via the Internet;
coupling a second client to the server through the Internet, wherein the second client comprises a capability to receive audio speech from a user,after receiving audio speech, the second client encodes the received audio speech, and after encoding the received audio speech, the second client transmits packets of encoded audio speech along to the server with a second value via the Internet;
at a server, receiving packets of encoded audio speech from two or more clients; and
at the server, servicing the encoded audio speech in an amount of processing time based on the first value received from the first client and the second value received from the second client,wherein the server comprises the capability to transmit responses to the first and second clients, and the response is a result of the server'"'"'s servicing of the encoded audio speech based on the first and second values received from the clients.
1 Assignment
0 Petitions
Accused Products
Abstract
Methods and systems for handling speech recognition processing in effectively real-time, via the Internet, in order that users do not experience noticeable delays from the start until they receive responsive feedback. A user uses a client to access the Internet and a server supporting speech recognition processing. The user inputs speech to the client, which transmits the user speech to the server in approximate real-time. The server evaluates the user speech, and provides responsive feedback to the client, again, in approximate real-time, with minimum latency delays. The client upon receiving responsive feedback from the server, displays, or otherwise provides, the feedback to the user.
69 Citations
18 Claims
-
1. A method comprising:
-
coupling a first client to a server through the Internet, wherein the first client comprises a capability to receive audio speech from a user, at the first client after receiving the audio speech, the first client encodes the received audio speech, and after encoding the received audio speech, the first client transmits packets of encoded audio speech along with a first value to the server via the Internet; coupling a second client to the server through the Internet, wherein the second client comprises a capability to receive audio speech from a user, after receiving audio speech, the second client encodes the received audio speech, and after encoding the received audio speech, the second client transmits packets of encoded audio speech along to the server with a second value via the Internet; at a server, receiving packets of encoded audio speech from two or more clients; and at the server, servicing the encoded audio speech in an amount of processing time based on the first value received from the first client and the second value received from the second client, wherein the server comprises the capability to transmit responses to the first and second clients, and the response is a result of the server'"'"'s servicing of the encoded audio speech based on the first and second values received from the clients. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method of on-line speech recognition comprising:
-
coupling a first client to a server through the Internet, wherein after receiving audio speech from a user, the first client encodes the audio speech before all of the audio speech is received, the first client comprises the capability to receive audio speech from a user in an uncompressed audio format, storing the encoded speech in one or more buffers, the first client packages the encoded audio speech into one or more packets to be transmitted over the Internet before all of the audio speech is received, and the first client transmits a packet of encoded audio speech along with a first value over the Internet before all of the audio speech is received; coupling a second client to the server through the Internet, wherein the second client comprises the capability to receive audio speech from a user in an uncompressed audio format, after receiving audio speech from a user, the second client encodes the audio speech before all of the audio speech is received, the second client stores the encoded speech in one or more buffers, the second client packages the encoded audio speech into one or more packets to be transmitted over the Internet before all of the audio speech is received, and the second client transmits a packet of encoded audio speech along with a second value over the Internet before all of the audio speech is received; at the server, receiving packets of encoded audio speech from two or more clients; at the server, decoding each of the packets of audio speech and storing the resultant speech into one or more buffers for the respective client; and at the server, formulating a response to the resultant speech from each of the two or more clients, wherein the server comprises the capability to transmit a response to the first and second clients, and the response is a result of the server'"'"'s formulating of the resultant speech in an amount of processing time based on the first and second values received from the clients. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16, 17, 18)
-
Specification