Distributed client-server speech recognition system
DCFirst Claim
1. A distributed speech recognition system for recognizing a speech input signal, the system comprising:
- at least one client station and a server station;
the client station including a processor configured to transmit a signal representative of the received speech input signal to the server station; and
the server station including a vocabulary speech recognizer for recognizing the received speech equivalent signal;
wherein the client station includes a local speech recognizer and a speech controller;
the speech controller being operative to direct at least part of the speech input signal to the local speech recognizer and, and wherein, respective portions of the speech recogntion of the speech input signal are processed by the client station and server station, independently.
8 Assignments
Litigations
0 Petitions
Accused Products
Abstract
A distributed speech recognition system includes at least one client station and a server station connected via a network, such as Internet. The client station includes means for receiving the speech input signal from a user. A speech controller directs at least part of the speech input signal to a local speech recognizer. The, preferably limited, speech recognizer is capable of recognizing at least part of the speech input, for instance a spoken command for starting full recognition. In dependence on the outcome of the recognition, the speech controller selectively directs a part of the speech input signal via the network to the server station. The server station includes means for receiving the speech equivalent signal from the network and a large/huge vocabulary speech recognizer for recognizing the received speech equivalent signal.
442 Citations
12 Claims
-
1. A distributed speech recognition system for recognizing a speech input signal, the system comprising:
-
at least one client station and a server station;
the client station including a processor configured to transmit a signal representative of the received speech input signal to the server station; and
the server station including a vocabulary speech recognizer for recognizing the received speech equivalent signal;
wherein the client station includes a local speech recognizer and a speech controller;
the speech controller being operative to direct at least part of the speech input signal to the local speech recognizer and, andwherein, respective portions of the speech recogntion of the speech input signal are processed by the client station and server station, independently. - View Dependent Claims (2, 3, 4, 5, 6)
the server station being operative to transfer a recognized word sequence back to the client station;
the client station including a selector for selecting a recognized word sequence from the word sequences respectively recognized by the recognizer in the client station and recognizer in the server station.
-
-
7. A method of recognizing a speech input signal in a distributed system including at least one client station and a server station;
- the method including;
receiving in the client station the speech input signal from a user;
recognizing at least part of the speech input signal in the client station;
selectively directing portions of a signal representative of a part of the speech input signal from the client station to the server station;
receiving the speech equivalent signal in the server station; and
recognizing the received speech equivalent signal in the server station using a speech recognizer. - View Dependent Claims (8)
- the method including;
-
9. A speech recognition client station including:
-
means for receiving a speech input signal from a user means for recognizing at least part of the speech input signal;
means for selectively directing a signal representative of a part of the speech input signal to a server station for recognition by a speech recognizer in the server station;
wherein, respective portions of the speech recogntion of the speech input signal are processed by the client station and server station, independently.
-
-
10. A method of handling a speech input signal in a client station of a distributed speech recognition system which further includes a server station;
- the method including;
receiving in the client station the speech input signal from a user;
recognizing at least part of the speech input signal in the client station;
selectively directing a signal representative of a part of the speech input signal from the client station to the server station for recognition by a large/huge vocabulary speech recognizer in the server station;
wherein,respective portions of the speech recogntion of the speech input signal are processed by the client station and server station, independently and the directing being in dependence on the outcome of the recognition in the client station. - View Dependent Claims (11, 12)
- the method including;
Specification