Method and system for aligning natural and synthetic video to speech synthesis

• US 6,862,569 B1
• Filed: 01/23/2003
• Issued: 03/01/2005
• Est. Priority Date: 08/05/1997
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Basso, Andrea, Beutnagel, Mark Charles, Ostermann, Joern
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Lerner, Martin
• Application Number:
  US10/350,225
• Time in Patent Office: 768 Days
• Field of Search: 704/258, 704/260, 704/267, 704/270, 704/276, 345/473, 345/706, 386/95, 715/500.1
• US Class Current: 704/260
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 2021/105 Synthesis of the lips movements from speech, e.g. for talking heads
• CPC Class Codes: H04N 19/20 using video object coding
• CPC Class Codes: H04N 19/46 Embedding additional information in the video signal during the compression process H04N19/517, H04N19/68, H04N19/70 take precedence
• CPC Class Codes: H04N 19/61 in combination with predictive coding

Abstract

According to MPEG-4'"'"'s TTS architecture, facial animation can be driven by two streams simultaneously—text, and Facial Animation Parameters. In this architecture, text input is sent to a Text-To-Speech converter at a decoder that drives the mouth shapes of the face. Facial Animation Parameters are sent from an encoder to the face over the communication channel. The present invention includes codes (known as bookmarks) in the text string transmitted to the Text-to-Speech converter, which bookmarks are placed between words as well as inside them. According to the present invention, the bookmarks carry-an encoder time stamp. Due to the nature of text-to-speech conversion, the encoder time stamp does not relate to real-world time, and should be interpreted as a counter. In addition, the Facial Animation Parameter stream carries the same encoder time stamp found in the bookmark of the text. The system of the present invention reads the bookmark and provides the encoder time stamp as well as a real-time time stamp to the facial animation system. Finally, the facial animation system associates the correct facial animation parameter with the real-time time stamp using the encoder time stamp of the bookmark as a reference.

Claims

1. A method for encoding a facial animation including at least one facial mimic and speech in the form of a text stream, comprising the steps of:

a) assigning a predetermined code to at least one facial mimic;

b) placing the predetermined code within a text stream, wherein the predetermined code points to a stream of facial mimics thereby indicating a synchronization relationship between the text stream and the facial mimic stream; and

c) encoding the test stream.

2. A data stream comprising facial animation data including at least one facial mimic and speech information, the data stream comprising:

a) a text stream containing speech information;

b) a facial mimic stream separate from the text stream and containing at least one facial mimic; and

c) means placed within the text stream for pointing to the facial mimic stream to indicate a synchronization relationship between the text stream and the facial mimic stream.

3. A method for encoding a facial animation, comprising steps of:

a) generating a facial mimic stream containing at least one facial mimic;

b) generating a text stream containing speech information and being separate from the facial mimic stream;

c) placing within the text stream a means for pointing to the facial mimics stream to thereby indicate a synchronization relationship between the text stream and the facial mimic stream; and

d) encoding the text stream.

4. A method for decoding a facial animation including speech and at least one facial mimic, comprising the steps of:

a) monitoring a text stream for a predetermined code corresponding to a facial mimic, wherein the predetermined code points to a stream of facial mimics established during an encoding process of the text stream, thereby indicating a synchronization relationship between the text stream and the facial mimic stream; and

b) sending a signal to a visual decoder to start a particular facial mimic upon detecting the presence of the predetermined code.

5. A method for decoding a facial animation including speech and at least one facial mimic of claim 4, wherein the correspondence between the predetermined code and the facial mimic is established during an encoding process of the text stream.