Output Format

Animation is output in the Speech Graphics proprietary file formats: Events (.event) and Regular Time Series (.rts).

Event Files

Animation is always output in the Speech Graphics proprietary Event (.event) file format, which contains original audio along with animation metadata and other synchronized information.

Event files are converted to other formats using the Maya plugin (see Converting Output).

RTS Files

In addition, animation can be obtained as plain text. When the "Extract Animation" box is checked in SGX-GUI, or the -e option is used on the command line, SGX will also output animation in a plain-text format that can be used independently of Maya. The Speech Graphics Regular Time Series (.rts) format describes a time series of multichannel data at a regular sample rate. The first row contains a single value which is the sample rate. The second row is a comma-separated sequence of channel labels. Each subsequent row contains a sample of the channel values at the given sample rate.

Here is an example of the .rts format:

CODE

30 
head.tx,head.ty,head.tz,head.rx,head.ry,head.rz,head.sx,head.sy,...
1.999987416,3.86E-06,-1.80E-06,-0.000571836,-0.002572273,-0.0001...
1.999848472,9.27E-05,-1.87E-05,-0.005927532,-0.026663633,-0.0065...
1.999549227,0.000318193,-5.29E-05,-0.016749984,-0.075345895,-0.0...
1.999104374,0.000668944,-0.000102617,-0.032516878,-0.146269352,-...
1.998546331,0.001117568,-0.00016447,-0.052116501,-0.234432717,-0...
1.997909577,0.001634493,-0.000234717,-0.074376584,-0.334562011,-...
1.997233413,0.002185685,-0.000309162,-0.097967676,-0.440676092,-...

Output Reports

In addition to the event files, the output directory also includes two files summarizing the batch:

_sgx_batch_TIMESTAMP.txt, containing a record of the batch command arguments
_sgx_batch_TIMESTAMP.csv, containing a processing report

where TIMESTAMP is in the format yyyymmddThhmmss; for example _sgx_batch_20190929T164937.

The processing report contains one row for each audio file, with the following format:

CODE

input,processing_status,transcript_status,phonetic_analysis_score,pre_roll,post_roll

The comma-separated elements are as follows:

property	values	description
input		The base name of the audio file.
processing status	0 or 1	Whether processing was successful.
transcript status	0 or 1	Whether a transcription of the speech was found.
phonetic analysis score	[0,1]	The accuracy of the phonetic lip sync analysis, determining to what extent it was used.
pre-roll	[0,...]	Duration of the pre-roll (in milliseconds).
post-roll	[0,...]	Duration of the post-roll (in milliseconds).

Below is an example batch report .csv file, viewed as a spreadsheet:

	processing status	transcript status	phonetic analysis score	pre-roll	post-roll
p364_025	1	1	0.84	18.21	42.79
p364_026	1	1	0.79	0	216.68
p364_027	1	0	0	15.9	16.41
p364_028	1	1	0.99	103.43	136.37
p364_029	1	1	0.95	0	401.91
p364_030	0	0	0	0	0
p364_031	1	1	0.91	13.43	136.37
p364_032	1	1	0.89	0	136.37
p364_033	1	1	0.65	103.43	0
p364_034	1	1	0.77	29.02	432.31
p364_035	1	1	0.99	0	0