Methods and apparatus for providing speech recognition services to communication system users
First Claim
1. A method of performing speech recognition, the method comprising the step of:
- monitoring a communication line for a signal indicative of a type of service to be provided to a user of the communication line;
selecting a first one of a plurality of speech recognition circuits having differing speech recognition capabilities as a function of the signal indicative of the type of service to be provided; and
connecting the first selected one of the plurality of speech recognition circuits to the communication line.
5 Assignments
0 Petitions
Accused Products
Abstract
Methods and apparatus for providing speech recognition capability to callers in a cost efficient manner as part of one or more telephone services are described. Multiple speech recognition units with differing capabilities and therefore implementation costs are provided. Calls are assigned to speech recognition circuits throughout a call based on a signal such as a service type identifier indicating the type of service to be provided to the caller. During different phases of a call different speech recognition units may be used. In addition, different amounts of speech recognition processing capability may be allocated to service a call at different points during a call. In this manner efficient use of available speech recognition resources can be achieved.
26 Citations
29 Claims
-
1. A method of performing speech recognition, the method comprising the step of:
-
monitoring a communication line for a signal indicative of a type of service to be provided to a user of the communication line;
selecting a first one of a plurality of speech recognition circuits having differing speech recognition capabilities as a function of the signal indicative of the type of service to be provided; and
connecting the first selected one of the plurality of speech recognition circuits to the communication line. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method of providing a speech recognition capability to peripheral devices included in a telephone system having a caller and a plurality of peripheral devices, the method comprising the steps of:
-
establishing a first connection, the first connection being between a caller and a first peripheral device including a first speech recognition circuit;
establishing a second connection which extends the first connection, the second connection being between the first peripheral device and a second peripheral device;
operating a first speech recognition circuit included in the first peripheral device to monitor the connection established between the caller and the second peripheral device, by the first and second connections, for speech; and
operating a DTMF tone generator included in the first peripheral device to generate a DTMF tone in response to the detection of a spoken number detected by the speech recognition circuit. - View Dependent Claims (13, 14, 15, 16, 17)
-
-
18. A method of providing a speech recognition service during a telephone call in a telephone system including a caller, a switch, a peripheral device and a plurality of distinct speech recognition units including a speaker independent speech recognition unit and a combined speaker independent and speaker dependent speech recognition unit, the method comprising the steps of:
-
monitoring the status of the telephone call to detect when the caller is coupled to a peripheral device;
utilizing the combined speaker independent and speaker dependent speech recognition circuit to perform a speech recognition operation during a first portion of a call; and
utilizing the speaker independent speech recognition circuit to perform a speaker independent speech recognition operation during a second portion of the call during the time period in which the caller is coupled to the peripheral device, the combined speaker independent and speaker dependent speech recognition circuit not being used during the second portion of the call. - View Dependent Claims (19, 20, 21, 22, 23, 24)
-
-
25. A telephone system comprising:
-
a telephone;
a first peripheral device for providing a service to a user of the telephone;
a second peripheral device including a speech recognition circuit, the speech recognition circuit including;
means for monitoring the connection established between the a caller using the telephone and the first peripheral device;
means for dynamically varying the amount of processing resources allocated to performing speech recognition on speech obtained from the telephone as a function of the stage of a telephone call; and
a switch for coupling the telephone to the first and second peripheral devices.
-
-
26. A telephone system, comprising:
-
a telephone;
a peripheral device for providing a service to a caller using the telephone;
a switch coupled to the telephone for connecting the telephone to the peripheral device;
a combined speaker independent and speaker dependent speech recognition circuit coupled to the switch;
a speaker independent speech recognition circuit coupled to the switch; and
a central processing unit coupled to the combined speech recognition circuit and the speaker independent speech recognition circuit for monitoring the status of a call connection between the switch and the peripheral device while the connection is being established and during the period that the call connection is maintained and dynamically switching between the use of the combined speech recognition circuit and the speaker independent speech recognition circuit, for recognizing speech transmitted on the call connection being monitored, as a function of the connection status. - View Dependent Claims (27, 28, 29)
-
Specification