Text-to-speech user's voice cooperative server for instant messaging clients

• US 9,026,445 B2
• Filed: 03/20/2013
• Issued: 05/05/2015
• Est. Priority Date: 10/03/2005
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Niemeyer, Terry Wade, Orozco, Liliana
• Primary Examiner(s): BAKER, MATTHEW H
• Application Number:
  US13/847,850
• Publication Number:
  US 20130218569A1
• Time in Patent Office: 776 Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 13/06 Elementary speech units used in speech synthesisers; Concatenation rules
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

A system and method to allow an author of an instant message to enable and control the production of audible speech to the recipient of the message. The voice of the author of the message is characterized into parameters compatible with a formative or articulative text-to-speech engine such that upon receipt, the receiving client device can generate audible speech signals from the message text according to the characterization of the author'"'"'s voice. Alternatively, the author can store samples of his or her actual voice in a server so that, upon transmission of a message by the author to a recipient, the server extracts the samples needed only to synthesize the words in the text message, and delivers those to the receiving client device so that they are used by a client-side concatenative text-to-speech engine to generate audible speech signals having a close likeness to the actual voice of the author.

Claims

1. A method comprising:

analyzing text within a body of a first user'"'"'s text instant message to determine text-to-speech synthesis control parameters that are to be used to produce a synthesized audible representation of the text within the body of the text instant message; and

extracting, from text-to-speech synthesis control parameters that are associated with the first user and comprise one or more voice synthesis control parameters which determine distinctive intelligible characteristics representative of the first user, a subset of the text-to-speech synthesis control parameters associated with the first user;

wherein the text to speech synthesis control parameters are compatible with a Local Frequency Oscillator (LFO) method of voice synthesis and are to be used to produce the synthesized audible representation of the text within the body of the text instant message.

2. The method of claim 1, further comprising sending the text instant message and the subset of text-to-speech synthesis control parameters, attached to the text instant message, to a second user'"'"'s device;

receiving the text instant message along with the subset of text-to-speech synthesis control parameters by the second user'"'"'s device; and

at the second user'"'"'s device, performing text-to-speech synthesis of the text instant message implementing the subset of text-to-speech synthesis control parameters to produce the synthesized audible representation of the text within the body of the text instant message having the distinctive intelligible characteristics representative of the first user.

3. The method of claim 2, wherein receiving the text instant message along with the subset of text-to-speech synthesis control parameters by the second user'"'"'s device comprises receiving the text instant message along with the subset of text-to-speech synthesis control parameters by a portable device.

4. The method of claim 1, wherein the first user is an author of the text instant message.

5. The method of claim 1, wherein extracting, from text-to-speech synthesis control parameters that are associated with the first user and comprise one or more voice synthesis control parameters which determine distinctive intelligible characteristics representative of the first user, a subset of the text-to-speech synthesis control parameters associated with the first user comprises extracting the subset from a server.

6. At least one computer-readable storage device encoded with computer-readable instructions which, when executed, causes performance of a method, the method comprising:

analyzing text within a body of a first user'"'"'s text instant message to determine text-to-speech synthesis control parameters that are to be used to produce a synthesized audible representation of the text within the body of the text instant message; and

extracting, from text-to-speech synthesis control parameters that are associated with the first user and comprise one or more voice synthesis control parameters which determine distinctive intelligible characteristics representative of the first user, a subset of the text-to-speech synthesis control parameters associated with the first user;

wherein the text to speech synthesis control parameters are compatible with a Local Frequency Oscillator (LFO) method of voice synthesis and are to be used to produce the synthesized audible representation of the text within the body of the text instant message.

7. The at least one computer-readable storage device of claim 6, wherein the method further comprises sending the text instant message and the subset of text-to-speech synthesis control parameters, attached to the text instant message, to a second user'"'"'s device.

8. The at least one computer-readable storage device of claim 7, wherein sending the text instant message and the subset of text-to-speech synthesis control parameters, attached to the text instant message, to a second user'"'"'s device comprises sending the text instant message from a portable device.

9. The at least one computer-readable storage device of claim 6, wherein the first user is an author of the text instant message.

10. The at least one computer-readable storage device of claim 6, wherein extracting, from text-to-speech synthesis control parameters that are associated with the first user and comprise one or more voice synthesis control parameters which determine distinctive intelligible characteristics representative of the first user, a subset of the text-to-speech synthesis control parameters associated with the first user comprises extracting the subset from a server.

11. A method, comprising:

receiving with a receiving device a text instant message together with one or more text-to-speech synthesis control parameters including one or more voice synthesis control parameters which determine distinctive intelligible characteristics representative of an author of the text instant message, the one or more text-to-speech synthesis control parameters representing a subset of a larger set of text-to-speech synthesis control parameters associated with the author and determining the distinctive intelligible characteristics representative of the author of the text instant message,

wherein receiving with a receiving device a text instant message together with one or more text-to-speech synthesis control parameters including one or more voice synthesis control parameters comprises receiving parameters compatible with a Local Frequency Oscillator (LFO) method of voice synthesis.

12. The method of claim 11, further comprising performing text-to-speech synthesis on the text instant message with the receiving device by using the one or more text-to-speech synthesis control parameters to produce a synthesized audible representation of the text instant message having the distinctive intelligible characteristics of the author.

13. The method of claim 12, further comprising deleting the one or more text-to-speech synthesis control parameters from the receiving device subsequent to performing the text-to-speech synthesis.

14. The method of claim 11, further comprising temporarily storing the one or more text-to-speech synthesis control parameters on the receiving device.