Personal Virtual Assistant
First Claim
1. A text to speech (TTS) engine adapted to receive text input and produce an output comprising a spoken version of the text input, the TTS engine including:
- an input for receiving text;
an algorithm for determining a pronunciation for words in the text;
a user configurable file storing a set of words and a phonetically spelled version of at least some of the words in the set of words;
wherein, when the user configurable file includes a phonetically spelled version of a given word in the input text, the TTS engine produces a spoken version of the phonetically spelled version of the given word.
0 Assignments
0 Petitions
Accused Products
Abstract
A computer-based virtual assistant includes a virtual assistant application running on a computer capable of receiving human voice communications from a user of a remote user interface and transmitting a vocalization to the remote user interface, the virtual assistant application enabling the user to access email and voicemail messages of the user, the virtual assistant application selecting a responsive action to a verbal query or instruction received from the remote user interface and transmitting a vocalization characterizing the selected responsive action to the remote user interface, and the virtual assistant waiting a predetermined period of time, and if no canceling indication is received from the remote user interface, proceeding to perform the selected responsive action, and if a canceling indication is received from the remote user interface halting the selected responsive action and transmitting a new vocalization to the remote user interface. Also a method of using the virtual assistant.
297 Citations
8 Claims
-
1. A text to speech (TTS) engine adapted to receive text input and produce an output comprising a spoken version of the text input, the TTS engine including:
-
an input for receiving text; an algorithm for determining a pronunciation for words in the text; a user configurable file storing a set of words and a phonetically spelled version of at least some of the words in the set of words; wherein, when the user configurable file includes a phonetically spelled version of a given word in the input text, the TTS engine produces a spoken version of the phonetically spelled version of the given word. - View Dependent Claims (2, 3)
-
-
4. A method of translating text to speech comprising:
-
providing an algorithm for pronouncing words; providing a file containing words; associating a phonetically spelled version of at least some of the words in the file with at least some of the words in the file; receiving a text input; producing a spoken version of each of the words in the text input; and when a given word in the text input is present in the file and includes a phonetically spelled version associated therewith, producing a spoken version of the phonetically spelled version of the given word. - View Dependent Claims (5, 6, 7, 8)
-
Specification