Application of emotion-based intonation and prosody to speech in text-to-speech systems

• US 7,401,020 B2
• Filed: 11/29/2002
• Issued: 07/15/2008
• Est. Priority Date: 11/29/2002
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Eide, Ellen M.
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US10/306,950
• Publication Number:
  US 20040107101A1
• Time in Patent Office: 2,055 Days
• Field of Search: 704/258, 704/260
• US Class Current: 704/258
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation
• CPC Class Codes: Y10S 715/977 Dynamic icon, e.g. animated or live action

Abstract

A text-to-speech system that includes an arrangement for accepting text input, an arrangement for providing synthetic speech output, and an arrangement for imparting emotion-based features to synthetic speech output. The arrangement for imparting emotion-based features includes an arrangement for accepting instruction for imparting at least one emotion-based paradigm to synthetic speech output, as well as an arrangement for applying at least one emotion-based paradigm to synthetic speech output.

Claims

1. A method of converting text to speech, said method comprising the steps of:

accepting text input;

providing synthetic speech output corresponding to the text input;

imparting emotion-based features to synthetic speech output;

said step of imparting emotion-based features comprising;

accepting instruction for imparting at least one emotion-based paradigm to synthetic speech output, wherein said step of accepting instruction further comprises accepting emotion-based commands from a user interface; and

applying at least one emotion-based paradigm to synthetic speech output, said step of applying at least one emotion-based paradigm to synthetic speech output comprising;

altering at least one segment to be used in synthetic speech output, whereby emotion in speech is reflected in how individual words or syllables are stressed;

altering at least one prosodic pattern to be used in synthetic speech output, whereby emotion in speech is reflected in prosodic patterns; and

selectably applying a single emotion-based paradigm over a single utterance of synthetic speech output;

or

applying a variable emotion-based paradigm over individual segments of an utterance of synthetic speech output.

2. The method according to claim 1, wherein said step of accepting instruction comprises accepting commands from an emotion-based markup language associated with the user interface.

3. The method according to claim 1, wherein said step of applying at least one emotion-based paradigm comprises altering at least one of:

prosody, intonation, and intonation intensity in synthetic speech output.

4. The method according to claim 1, wherein said step of applying at least one emotion-based paradigm comprises altering at least one of speed and amplitude in order to affect prosody, intonation and intonation intensity in synthetic speech output.