Source-dependent text-to-speech system
First Claim
Patent Images
1. A method of generating speech from text messages, comprising:
- determining a speech feature vector for a voice associated with a source of a first text message;
comparing the speech feature vector to a plurality of speaker models, wherein the plurality of speaker models are unrelated to the source of the first text message;
based on the comparison, selecting one of the speaker models as a preferred match for the voice;
associating the selected speaker model with the source of the first text message;
if the speech feature vector cannot be determined, selecting one of the speaker models as a default selection;
generating speech from the text message based on the selected speaker model; and
automatically generating speech from subsequent text messages received from the source of the first text message, based on the selected speaker model.
1 Assignment
0 Petitions
Accused Products
Abstract
A method of generating speech from text messages includes determining a speech feature vector for a voice associated with a source of a text message, and comparing the speech feature vector to speaker models. The method also includes selecting one of the speaker models as a preferred match for the voice based on the comparison, and generating speech from the text message based on the selected speaker model.
-
Citations
34 Claims
-
1. A method of generating speech from text messages, comprising:
-
determining a speech feature vector for a voice associated with a source of a first text message; comparing the speech feature vector to a plurality of speaker models, wherein the plurality of speaker models are unrelated to the source of the first text message; based on the comparison, selecting one of the speaker models as a preferred match for the voice; associating the selected speaker model with the source of the first text message; if the speech feature vector cannot be determined, selecting one of the speaker models as a default selection; generating speech from the text message based on the selected speaker model; and automatically generating speech from subsequent text messages received from the source of the first text message, based on the selected speaker model. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A voice match server, comprising:
-
an interface operable to; receive a speech feature vector for a voice associated with a source of a first text message; and communicate a command to a text-to-speech server instructing the text-to-speech server to generate speech from the text message based on a selected speaker model; and a processor operable to; compare the speech feature vector to a plurality of speaker models, wherein the plurality of speaker models are unrelated to the source of the text message; select one of the speaker models as a preferred match for the voice based on the comparison; associate the selected speaker model with the source of the first text message; and select one of the speaker models as a default selection if the interface does not receive the speech feature vector; and the interface further operable to communicate a command to a text-to-speech server instructing the text-to-speech server to automatically generate speech from subsequent text messages received from the source of the first text message, based on the selected speaker model. - View Dependent Claims (12, 13, 14, 15, 16, 17)
-
-
18. An endpoint, comprising:
-
a first interface operable to receive a first text message from a source; and a processor operable to; determine a speech feature vector for a voice associated with a source of the text message; compare the speech feature vector to a plurality of speaker models, wherein the plurality of speaker models are unrelated to the source of the first text message; select one of the speaker models as a preferred match for the voice based on the comparison; associate the selected speaker model with the source of the first text message; select one of the speaker models as a default selection if the processor cannot determine the speech feature vector; generate speech from the text message based on the selected speaker model; and automatically generate speech from subsequent text message received from the source of the first text message, based on the selected speaker model; and a second interface operable to output the generated speech to a user. - View Dependent Claims (19, 20, 21)
-
-
22. A system, comprising:
-
a voice match server operable to; compare a speech feature vector, for a voice associated with a source of a first text message, to a plurality of speaker models, wherein the plurality of speaker models are unrelated to the source of the first text message; and select one of the speaker models as a preferred match for the voice based on the comparison; associate the selected speaker model with the source of the first text message; select one of the speaker models as a default selection if the speech feature vector cannot be determined; and a text-to-speech server operable to generate speech from the text message based on the selected speaker model; and the text-to-speech server further operable to automatically generate speech from subsequent text messages received from the source of the first text message, based on the selected speaker model. - View Dependent Claims (23, 24, 25, 26)
-
-
27. Software embodied in a non-transitory tangible computer-readable medium, operable to perform the steps of:
-
determining a speech feature vector for a voice associated with a source of a first text message; comparing the speech feature vector to a plurality of speaker models, wherein the plurality of speaker models are unrelated to the source of the first text message; based on the comparison, selecting one of the speaker models as a preferred match for the voice; associating the selected speaker model with the source of the first text message; selecting one of the speaker models as a default selection if the speech feature vector cannot be determined; generating speech from the text message based on the selected speaker model; and automatically generating speech from subsequent text messages received from the source of the first text message, based on the selected speaker model. - View Dependent Claims (28, 29, 30)
-
-
31. A system, comprising:
-
means for determining a speech feature vector for a voice associated with a source of a first text message; means for comparing the speech feature vector to a plurality of speaker models, wherein the plurality of speaker models are unrelated to the source of the first text message; means for selecting one of the speaker models as a preferred match for the voice based on the comparison; means for associating the selected speaker model with the source of the first text message; means for selecting one of the speaker models as a default selection if the speech feature vector cannot be determined; means for generating speech from the text message based on the selected speaker model; and means for automatically generating speech from subsequent text messages received from the source of the first text message, based on the selected speaker model. - View Dependent Claims (32, 33, 34)
-
Specification