When testing adapted acoustic models, I use pocketsphinx_batch to produce a hypothesis file, and then interpret this with word_align.pl. The hyp file results in output such as the following:
GALA MABU NGANGAN GALA JUYU (wav/Yawuru_test/BB_T0_gala -5847)
Could someone please tell me what the final number (here -5847) represents?
Thanks, Virginia
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
When testing adapted acoustic models, I use pocketsphinx_batch to produce a hypothesis file, and then interpret this with word_align.pl. The hyp file results in output such as the following:
GALA MABU NGANGAN GALA JUYU (wav/Yawuru_test/BB_T0_gala -5847)
Could someone please tell me what the final number (here -5847) represents?
Thanks, Virginia
This is a path score computed by decoder with the model. It does not have any meaning, you can ignore it.