5.3.3 CI Phone Models: Multi-Path Silence Training
The details of multi-path silence training are explained in Section 5.2.4. This process is nearly identical for context independent phone models. The only difference, once again, is the structure of the language model which now has three levels instead of two. The extra level accounts for the phonetic contents of each word. Go to the directory:
Command: isip_recognize -param params_sp.sof -verbose brief -list $ISIP_TUTORIAL/research/isip/databases/lists/identifiers_train.sof Version: 1.23 (not released) 2003/05/21 23:10:45 loading audio database: $ISIP_TUTORIAL/research/isip/databases/db/tidigits_audio_db.sof *** no symbol graph database file was specified *** loading transcription database: $ISIP_TUTORIAL/research/isip/databases/db/tidigits_trans_word_db.sof loading front-end: $ISIP_TUTORIAL/recipes/frontend.sof loading language model: $ISIP_TUTORIAL/models/ci_phone_models/lm_phone_jsgf_sil.sof loading statistical model pool: $ISIP_TUTORIAL/models/ci_phone_models/smp_phone_sil.sof loading configuration file: $ISIP_TUTORIAL/sections/s05/s05_03_p03/config.sof starting iteration: 0 processing file 1 (ae_12a): $ISIP_TUTORIAL/research/isip/databases/sof_8k/train/ae_12a.sof retrieving annotation graph for identifier: ae_12a, level: word transcription: ONE TWO average utterance probability: -70.621869668053364, number of frames: 110 processing file 2 (ae_1a): $ISIP_TUTORIAL/research/isip/databases/sof_8k/train/ae_1a.sof retrieving annotation graph for identifier: ae_1a, level: word transcription: ONE .... |
