Methods and apparatus for initiating a voice-dialing operation
First Claim
1. A method of performing a voice dialing operation, the method including the steps of:
- establishing a connection between a telephony device and a network based speech recognition device located in a communications network, said telephony device being capable of coupling said user to, at most, one network based speech recognition device in response to detecting speech used to initiate a voice dialing operation, the step of establishing a connection including the steps of;
operating the telephony device to perform speech recognition on audio signals received by the telephony device to determine if a word used to initiate a voice dialing operation was spoken; and
in response to determining that the received audio signals include said word used to initiate a communication operation, connecting the telephony device to said network based speech recognition device;
wherein said network based speech recognition device is an intelligent peripheral, the method further comprising the step of;
operating the intelligent peripheral to perform a second speech recognition operation to determine at least part of a telephone number.
6 Assignments
0 Petitions
Accused Products
Abstract
Hands free voice dialing telephony devices that can perform relatively simple speech recognition, e.g., to recognize one or a few words corresponding to a command to initiate voice dialing, are described. Speech recognition models stored in the telephony devices can be relatively small and may be either of a speaker dependent or speaker independent type. In response to detecting a command to perform a voice dialing operation the telephony device establishes a connection with a voice dialing intelligent peripheral (IP). The IP includes far greater speech recognition capabilities than the individual telephone devices and is responsible for supporting voice dialing operations associated with a plurality of voice dialing service subscribers. The IP performs speech recognition on speech provided by individual telephony devices and outputs telephone numbers corresponding to recognized spoken names. Telephony devices are coupled by the telephone network to destination telephones corresponding to the telephone numbers output by the IP. In one embodiment, speech recognition models are generated by the IP from speech transmitted from the individual telephony devices. The generated model or models are then stored in the telephony devices for use during speech recognition operations. Thus, processing resources required to generate speech recognition models can be located in a centralized network accessible location.
-
Citations
16 Claims
-
1. A method of performing a voice dialing operation, the method including the steps of:
-
establishing a connection between a telephony device and a network based speech recognition device located in a communications network, said telephony device being capable of coupling said user to, at most, one network based speech recognition device in response to detecting speech used to initiate a voice dialing operation, the step of establishing a connection including the steps of;
operating the telephony device to perform speech recognition on audio signals received by the telephony device to determine if a word used to initiate a voice dialing operation was spoken; and
in response to determining that the received audio signals include said word used to initiate a communication operation, connecting the telephony device to said network based speech recognition device;
wherein said network based speech recognition device is an intelligent peripheral, the method further comprising the step of;
operating the intelligent peripheral to perform a second speech recognition operation to determine at least part of a telephone number. - View Dependent Claims (2)
operating the intelligent peripheral to output a telephone number as a function of the result of the second speech recognition operation.
-
-
3. A method of performing voice dialing, the method including the step of:
-
establishing a connection between a telephony device and a communications device located in a communications network, said communications device being a network based speech recognition device, said telephony device being capable of coupling said user to, at most, one network based speech recognition device in response to detecting speech used to initiate a voice dialing operation, the step of establishing a connection including the steps of;
operating the telephony device to perform a first speech recognition operation on audio signals received by the telephony device to determine if a word used to initiate a voice dialing operation was spoken; and
in response to determining that the received audio signals include said word used to initiate a communication operation, connecting the telephony device to said communications device;
wherein the first speech recognition operation attempts to recognize a first set of words; and
wherein the second speech recognition operation involves examining audio signals obtained from the telephony device in an attempt to recognize a second set of words which includes at least three times the number of words included in the first set of words. - View Dependent Claims (4, 5, 6, 7)
-
-
8. A method of performing a voice dialing operation, the method including the step of:
-
establishing a connection between a telephony device and a communications device located in a communications network, said communications device being a network based speech recognition device, said telephony device being capable of coupling said user to, at most, one network based speech recognition device in response to detecting speech used to initiate a voice dialing operation, the step of establishing a connection including the steps of;
operating the telephony device to perform speech recognition on audio signals received by the telephony device to determine if speech used to initiate a voice dialing operation was spoken, said speech recognition including a first speech recognition operation; and
in response to determining that the received audio signals include speech used to initiate a voice dialing operation;
i) connecting the telephony device to said communications device, ii) operating said communications device to perform a second speech recognition operation, and iii) connecting the telephone device to an additional telephony device using a telephone number determined by the communications device as a function of said second speech recognition operation;
wherein the first speech recognition operation attempts to recognize a first set of words; and
wherein the second speech recognition operation involves examining audio signals obtained from the telephony device in an attempt to recognize a second set of words which includes at least fifteen times the number of words included in the first set of words. - View Dependent Claims (9)
-
-
10. A system for performing a voice dialing operation, comprising:
-
a first telephony device including first means for performing speech recognition on speech received by the first telephony device to detect the presence of speech used to initiate a voice dialing operation, said first telephony device being capable of coupling said user to, at most, one network based speech recognition device in response to detecting speech used to initiate a voice dialing operation; and
a communications network, coupled to the telephony device, the communications network including;
i. said one network based speech recognition device, said one network based speech recognition device including second means for performing speech recognition on audio signals received from the first telephony device; and
ii. means for routing signals from the first telephony device to a second telephony device, the routing being performed as a function of the result of a speech recognition operation performed on speech received from the first telephony device. - View Dependent Claims (11, 12, 13, 14, 15, 16)
means for generating a speech recognition model from speech provided by the first telephony device; and
means for outputting the generated speech recognition model to said first telephony device.
-
-
13. The system of claim 12, wherein the first telephony device includes:
means for storing the speech recognition model.
-
14. The system of claim 10, wherein the first means for performing speech recognition includes speech recognition circuitry.
-
15. The system of claim 10, wherein the means within said communications network for performing a speech recognition operation is a network server.
-
16. The system of claim 10, wherein the communications network is the Internet.
Specification