Client/server speech processor/recognizer
First Claim
1. In a client server architecture, a method of speech or voice utterances processing comprising the steps of:
- inputting into and digitizing voiced utterances by the client portion of the client server architecture as the utterances occur,extracting and quantizing features from said digitized voice utterances within said client computer system,organizing said extracted and quantized features into a protocol for sending,sending said quantized features to a server computing system,recognizing and decoding said quantized features into a response, andsending said response back to said client computing system, wherein said response is received as the voiced utterances occur in real time.
12 Assignments
0 Petitions
Accused Products
Abstract
A real-time or streaming speech processing system and method is disclosed with capabilities distributed between and client and a server where the server may be reached via the Internet. The speech processing entails digitizing and converting the utterances to features extracted to help the processing. The features are sent via a communications channel to the server where the recognition occurs. The features extracted allow low bandwidth channels to be used with still maintaining real-time response. The recognizer will determine the most likely text representing the utterances and return the text to the client. The system can be used to identify and/or verify who is speaking.
413 Citations
16 Claims
-
1. In a client server architecture, a method of speech or voice utterances processing comprising the steps of:
-
inputting into and digitizing voiced utterances by the client portion of the client server architecture as the utterances occur, extracting and quantizing features from said digitized voice utterances within said client computer system, organizing said extracted and quantized features into a protocol for sending, sending said quantized features to a server computing system, recognizing and decoding said quantized features into a response, and sending said response back to said client computing system, wherein said response is received as the voiced utterances occur in real time. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. Client/Server apparatus for processing voice utterances comprising:
-
means for inputting into and for digitizing voiced utterances by the client portion of the client server apparatus as the utterances occur, means for extracting and for quantizing features from said digitized voice utterances, means for organizing said extracted and quantized features into a protocol for sending, means for sending said quantized features to the server portion of the client server apparatus, means for recognizing and for decoding said quantized features into a response, and means for sending said response back to said client portion of the client server apparatus, wherein said response is received as the voiced utterances occur in real time. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
Specification