Hi,
May I know whether there is an easy way to get the alignment information (timing) of the phoneme during training in SphinxTrain, or the best is there exist a visualization tool which can provides labeling information against waveform. If both is not possible, any clues to modify the codes to make it possible? Thanks you very much in advance.
Tien Ping
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Finally clear my doubt, the alignment information can only get from the recognizer like sphinx3/4. I guess for Sphinx4, I will need to use the grammar ForcedAlignerGrammar.java as a replacement for N-gram.
TP
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
May I know whether there is an easy way to get the alignment information (timing) of the phoneme during training in SphinxTrain, or the best is there exist a visualization tool which can provides labeling information against waveform. If both is not possible, any clues to modify the codes to make it possible? Thanks you very much in advance.
Tien Ping
Finally clear my doubt, the alignment information can only get from the recognizer like sphinx3/4. I guess for Sphinx4, I will need to use the grammar ForcedAlignerGrammar.java as a replacement for N-gram.
TP