Philipp Klumpp

Thank you very much!

Thank you very much! I checked out their PTM model, but again the feat.params say: -lowerf 130 -upperf 6800 -nfilt 25 -transform dct -lifter 22 -feat 1s_c_d_dd -svspec 0-12/13-25/26-38 -agc none -cmn current -varnorm no

Hello everyone, I am currently working with Sphinx4 and wanted to try out both continuous and ptm German acoustic models. I downloaded them from here: https://sourceforge.net/projects/cmusphin/file/Acoustic%20and%20Language%20Models/German/ When I downloaded the "cmusphinx-de-ptm-voxforge-5.2.tar.gz", I was really confused when reading the feat.params file. It says "-feat 1s_c_d_dd", which is used by continuous models if I got this right (Source: https://cmusphinx.github.io/wiki/acousticmodeltypes/)....

Hello all, I have used Pocketsphinx multiple times now to perform speech recognition tasks on Android devices. Most recently, I tried to detect a single word with a grammar, and afterwards obtain time stamps for each of the segments. However, it turned out that the time stamps do not match the actual times from the file. It always tells me that the word was detected right in the beginning of the file, after 7 frames of SILence. This is my jsgf: #JSGF V1.0; grammar neighbors; public <kompliment> =...