im a newbie at pocket sphinx and i want to get some data from the recognition. now i have segmentation data but i want to know how to get the real time of a segment(the time in the audio file), like if i get an audio that is "Hello World" but there are some silence, i want to get the time with the silence to.
Last edit: Fernando Jimenez Gordillo 2016-10-13
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
im a newbie at pocket sphinx and i want to get some data from the recognition. now i have segmentation data but i want to know how to get the real time of a segment(the time in the audio file), like if i get an audio that is "Hello World" but there are some silence, i want to get the time with the silence to.
Last edit: Fernando Jimenez Gordillo 2016-10-13
You can get words with times with segments iterator. Everything else is silence.
but in a 25 seconds audio, the ps_get_all_time mark 22.89 seconds and idont know why
ps_get_all_time returns seconds of speech, not overall seconds. If you want overall seconds you need to count yourself.
can u share your project code with us?