Mpeg4-Visemes Animation Curve File (.csv)
This is a file that records animation curves for each phoneme of Mpeg4-Visemes in chronological order.
It is intended to be read by many libraries as a CSV file with a header.
File Contents
Illustratively, it is a text file that records animation curves for each phoneme as shown below.
The first line indicates the contents of each column, and from the second line onward, the analysis results are described.
time,PP,FF,TH,DD,kk,CH,SS,nn,RR,aa,E,ih,oh,ou,Vol,tongue_up
0.0000,0.0353,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,-96.0000,0.0000
0.0100,0.0684,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,-96.0000,0.0000
0.0200,0.1154,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,-96.0000,0.0000
0.0300,0.1755,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0012,-96.0000,0.0000
0.0400,0.2409,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0069,-96.0000,0.0000
0.0500,0.3008,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0212,-36.0033,0.0000
0.0600,0.3459,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0473,-27.7492,0.0000
0.0700,0.3719,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0872,-25.8695,0.0000
~~~
1.1900,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,-96.0000,0.0000
1.2000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,-96.0000,0.0000
1.2100,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,-96.0000,0.0000
1.2200,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,0.0000,-96.0000,0.0000
time
Represents the time for the audio file. The unit is seconds.
PP,FF,TH,DD,kk,CH,SS,nn,RR,aa,E,ih,oh,ou
These columns correspond to the mouth shapes of Mpeg4-Visemes.
It is assumed that each phoneme is assigned to a prepared morph target. The unit is morphing amount.
Vol
Represents the volume corresponding to the "time" column.
Decibels are 0.0 for maximum volume, and the larger the negative value, the lower the volume. In this result, -96 means silence.
Note that -96 to 0.0 does not mean the volume increases linearly.
This value is output as a reference for applications.
Use it as a reference when you want to open the mouth wider when the volume is high.
The unit is decibels (dB).
tongue_up
Represents the height of the tongue tip corresponding to the "time" column.
It is assumed to be assigned to the morph target of the tongue tip. It can be used when you want to move the mouth shape and tongue tip separately.
Notes
It does not fully comply with the international standard specification for CSV. The CSV extension is used as a comma-separated file.