Advanced tools for speech synchronized animation

• US 5,689,618 A
• Filed: 05/31/1995
• Issued: 11/18/1997
• Est. Priority Date: 02/19/1991
• Status: Expired due to Term

• Current Assignee: Activision Publishing Incorporated (Microsoft Corporation)
• Original Assignee: Brightmail, Inc. (Gen Digital Inc.)
• Inventors: Gasper, Elon, Wesley, Richard
• Primary Examiner(s): Tung, Kee M.
• Application Number:
  US08/457,023
• Time in Patent Office: 902 Days
• Field of Search: 395/152, 395/154, 395/2.69, 395/2.85, 395/2, 395/2.1, 395/2.79, 364/410, 434/307 R
• US Class Current: 704/276
• CPC Class Codes: G06T 13/205 driven by audio data
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 2021/105 Synthesis of the lips movements from speech, e.g. for talking heads
• CPC Class Codes: G11B 27/034 on discs G11B27/036, G11B27/038 take precedence
• CPC Class Codes: G11B 27/10 Indexing; Addressing; Timing or synchronising; Measuring tape travel
• CPC Class Codes: G11B 27/34 Indicating arrangements indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D
• CPC Class Codes: Y10S 345/956 Language driven animation
• CPC Class Codes: Y10S 345/957 Actor

Abstract

A random access animation user interface environment referred to as interFACE enabling a user to create and control animated lip-synchronized images or objects utilizing a personal computer for use in the users programs and products. A real-time random-access interface driver (RAVE) together with a descriptive authoring language (RAVEL) is used to provide synthesized actors ("synactors"). The synactors may represent real or imaginary persons or animated characters, objects or scenes. The synactors may be created and programmed to perform actions including speech which are not sequentially pre-stored records of previously enacted events. Furthermore, animation and sound synchronization may be produced automatically and in real-time. Sounds and visual images of a real or imaginary person or animated character associated with those sounds are input to a system and may be decomposed into constituent parts to produce fragmentary images and sounds. A set of characteristics is utilized to define a digital model of the motions and sounds of a particular synactor. The general purpose system is provided for random access and display of synactor images on a frame-by-frame basis, which is organized and synchronized with sound. Both synthetic speech and digitized recording may provide the speech for synactors.

Claims

1. For a programmed computer having a memory and a real-time random access animation and vivification engine driver, an apparatus for providing a voice sound for a synactor for sound-animation synchronization, the apparatus comprising:

a voice synthesizer coupled to the computer for producing synthesizer phonemes, the voice synthesizer including;

first means for receiving speech samples derived from input audio data and for providing a sample speech signal representing the speech samples;

first segmentation means coupled to the first means for extracting from the sample speech signal the speech samples in accordance with a predetermined speech segmentation plan, the first segmentation means for providing constituent speech segments;

second means for receiving speech text and for providing a speech text signal representing the speech text;

second segmentation means coupled to the second means for segmenting the speech text signal to provide constituent text segments in accordance with the predetermined speech segmentation plan;

encoding means for encoding the constituent speech segments to provide encoded constituent speech segments; and

combining means for combining the encoded constituent speech segments to provide a speech signal representative of animated speech corresponding to the speech text where each of the constituent speech segments corresponds to at least one of the constituent text segments;

means for creating a voice reconciliation phoneme table, the voice reconciliation phoneme table including the synthesizer phonemes;

means for providing a synactor model phoneme table, the synactor model phoneme table including synactor phonemes for the voice sound of the synactor;

means for determining which of the synthesizer phonemes are unrecognized as compared to the synactor model phoneme table;

means for finding substitute phonemes from the synactor model phoneme table for the unrecognized phonemes in the voice reconciliation phoneme table;

means for creating a generic phoneme table, the generic phoneme table including recognized synthesizer phonemes from the voice reconciliation phoneme table and the substitute phonemes; and

means for using the generic phoneme table, the voice reconciliation phoneme table and the synactor model phoneme table to provide a runtime reconciled phocode table for using the voice synthesizer to provide voice sound for the synactor without modifying the synactor model phoneme table.

2. The apparatus of claim 1 further comprising:

input means coupled to the first and second means for providing the input audio data and the speech text;

storage means coupled for storing the encoded constituent speech segments; and

at least one predefined voice file for storing the encoded constituent segments in the storage means, the predefined voice file including a language library, recording library and a voice library.

3. The apparatus of claim 1 wherein the first and second means are coupled to input means for providing the input audio data and the speech text to the first and second means.

4. The apparatus of claim 3 further comprising storage means for storing the constituent speech segments.

5. The apparatus of claim 4 further comprising a predefined voice file for storing the constituent speech segments with the storage means.

6. The apparatus of claim 5 wherein the speech samples are input to the first means in a selected voice, the predefined voice file being identified as the speech samples for the selected voice of a selected person.