System and method for personalized text-to-voice synthesis

1. A communication device for audibly outputting a received text message to a user in an output voice, the device comprising:

a) means for receiving data representing voice characteristic information associated with a sender of the text message, wherein the data representing the voice characteristic information defines the voice characteristic information as a set of voice deltas, each of the voice deltas representing a difference between a desired voice characteristic of the output voice and a corresponding predefined voice characteristic of a standard voice,

b) a processor for synthesizing an output voice in accordance with the voice characteristic information and said standard voice, wherein the output voice mimics a voice selected by the sender and the standard voice is a reference voice for use by a plurality of communication devices; and

c) an output for audibly presenting the text message to the user using the output voice.

2. The communication device of claim 1 , where the text message is an electronic mail message.

3. The communication device of claim 1 , wherein the text message is an instant message.

4. The communication device of claim 1 , wherein the voice selected by the send is the sender's voice.

5. The communication device of claim 1 , further including means for retrieving the standard voice along with the voice deltas.

6. A method of audibly outputting a received text message to a user via a communication device, the method comprising:

retrieving voice characteristic information associated with a sender of the received text message, the voice characteristic information defining a set of voice deltas, each of the voice deltas representing a difference between a desired voice characteristic of a voice selected by the sender and a corresponding predefined voice characteristic of a standard voice, the standard voice being a reference voice for use by a plurality of communication devices;

synthesizing an output voice in accordance with the voice characteristic information and the predefined voice characteristic of the standard voice, the output voice mimicking the voice selected by the sender; and

audibly outputting the received text message using the output voice.

7. A computer readable medium comprising computer-readable instructions, which when executed by a computer or a communication device, causes the computer or communication device to implement the method of claim 6 .

8. The method of claim 6 , wherein the voice selected by the sender is the sender's voice.

9. The method of claim 6 , comprising retrieving the predefined voice characteristic of the standard voice.

10. A communication device for audibly outputting a received text message to a user, the device comprising:

a processor to receive data representing voice characteristic information associated with a sender of the received text message, the voice characteristic information defining a set of voice deltas, each of the voice deltas representing a difference between a desired voice characteristic of a voice selected by the sender and a corresponding predefined voice characteristic of a standard voice, the standard voice being a reference voice for use by a plurality of communication devices and synthesize an output voice in accordance with the voice characteristic information and the corresponding predefined voice characteristic of the standard voice, the output voice mimicking the voice selected by the sender; and

an output operatively coupled to the processor to audibly output the received text message to the user using the output voice.

11. The method of claim 10 , wherein the text message is an electronic mail message.

12. The method of claim 10 , wherein the text message is an instant message.

13. The communication device of claim 10 , wherein the voice selected by the send is the sender's voice.

14. The communication device of claim 10 , wherein the processor retrieves the predefined voice characteristic of the standard voice.