Post-synchronizing an information stream
First Claim
1. A method of post-synchronizing an information stream, which information stream comprises an audio signal (A) and a video signal (V), the method comprising the step of:
- performing a translation process (7) to obtain at least one translated audio signal (A*), characterized in that the method comprises the steps of;
tracking (2) said video signal (V) to obtain original lip-objects (lo);
replacing (3,4) said original lip-objects (lo) with new lip-objects (lo*), said new lip-objects (lo*) corresponding to said translated audio signal (A*).
0 Assignments
0 Petitions
Accused Products
Abstract
The invention provides a method for post-synchronizing an information stream. Original lip-objects (lo) are obtained (2) from a video signal (V). These original lip-objects (lo) are replaced (3,4) with new lip-objects (lo*), which correspond to a translated audio signal (A*). Lip-objects (lo) can be obtained from the video signal (V) by using an object-oriented coding technique, e.g. MEG-4. The coding standard MPEG-4 offers the facilities to manipulate the lip-objects (lo). Several configurations are presented. The new lip-objects (lo*) can be obtained by tracking a further video signal or by using a database with visemes or lip-parameters. The invention is suitable for a communication network, e.g. for video-conferencing. A multi-language information stream comprises a plurality of audio signals (A,A*) and a plurality of lip-objects (lo,lo*) that are each linked to one of the audio signals (A,A*). This gives the possibility to select at the receiver a desired language. An advantage of the invention is that lip-movements better correspond to the translated audio.
20 Citations
14 Claims
-
1. A method of post-synchronizing an information stream, which information stream comprises an audio signal (A) and a video signal (V), the method comprising the step of:
-
performing a translation process (7) to obtain at least one translated audio signal (A*), characterized in that the method comprises the steps of;
tracking (2) said video signal (V) to obtain original lip-objects (lo);
replacing (3,4) said original lip-objects (lo) with new lip-objects (lo*), said new lip-objects (lo*) corresponding to said translated audio signal (A*). - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A transmitter for transmitting an information stream comprising at least one translated audio signal (A*) and a video signal (V),
characterized in that the transmitter comprises: -
tracking means (2) for tracking said video signal (V) to obtain original lip-objects (lo);
means (4) for adding new lip-objects (lo*) to the information stream to replace said original lip-objects (lo), the new lip objects (lo*) corresponding to said translated audio signal (A*). - View Dependent Claims (8)
-
-
9. A receiver for receiving an information stream comprising an audio signal (A) and a video signal (V),
characterized in that the receiver comprises: -
translation means (7) for performing a translation process to obtain a translated audio signal (A*);
tracking means (2) for tracking said video signal (V) to obtain original lip-objects (lo);
means (3,4) for adding to the information stream, new lip-objects (lo*) that correspond to said translated audio signal (A*); and
outputting means (5,8) for outputting said translated audio signal (A*) and said video signal (V*), in which video signal (V*) said original lip-objects (lo) have been replaced (4) with said new lip-objects (lo*).
-
-
10. A receiver for receiving an information stream comprising a translated audio signal (A*) and a video signal (V),
characterized in that the receiver comprises: -
tracking means (2) for tracking said video signal (V) to obtain original lip-objects (lo);
means (3,4) for adding to the information stream, new lip-objects (lo*) that correspond to said translated audio signal (A*);
outputting means (5,8) for outputting said translated audio signal (A*) and said video signal (V*), in which video signal (V*) said original lip-objects (lo) have been replaced (4) with said new lip-objects (lo*).
-
-
11. A receiver for receiving an information stream comprising:
- a video signal (V′
), a plurality of audio signals (A,A*, . . . ) relating to different languages and a plurality of lip-objects (lo,lo*, . . . ), which lip-objects (lo,lo*, . . . ) are each linked to at least one of said plurality of audio signals (A,A*, . . . );
which receiver comprises;
a selector (10) for obtaining a selected audio signal from said plurality of audio signals (A,A*, . . . );
outputting means (5,8) for outputting said selected audio signal and said video signal (V′
), said video signal comprising selected lip-objects, which lip-objects are linked to said selected audio signal.
- a video signal (V′
-
12. A communication system comprising:
-
a plurality of stations (ST1,ST2, . . . ,STN) comprising means (T1,T2, . . . ,TN) for transmitting and means (R1,R2, . . . ,RN) for receiving an information stream, which information stream comprises an audio (A) and a video signal (V); and
a communication network (CN) for linking said stations (ST1,ST2, . . . ,STN);
characterized in that the communication system comprises;
means for performing a translation process to obtain at least one translated audio signal (A*);
means for tracking said video signal (V) to obtain original lip-objects (lo); and
means for replacing said original lip-objects (lo) with new lip-objects (lo*) corresponding to said translated audio signal (A*).
-
-
13. An information stream comprising a video signal (V′
- ) and a plurality of audio signals (A,A*, . . . ) relating to different languages,
characterized in that said information stream further comprises;
a plurality of lip-objects (lo,lo*, . . . ) that are each linked to at least one of said plurality of audio signals (A,A*, . . . ). - View Dependent Claims (14)
- ) and a plurality of audio signals (A,A*, . . . ) relating to different languages,
Specification