I have one doubt regarding working of decoder. Initially I trained models with some utterances and tested on the same sentences which are used in training, uttered by different speaker. For generating language model and dictionary I have uploaded all the sentences used in training to lmtool. Now the case is different. In testing data some extra words are present. By including those words into the dictionary with the corresponding phoneme sequence will I able to decode those extra words. Is there anything I need to do modification with respect to language model. Please help me. Thanks in advance.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I have one doubt regarding working of decoder. Initially I trained models with some utterances and tested on the same sentences which are used in training, uttered by different speaker. For generating language model and dictionary I have uploaded all the sentences used in training to lmtool. Now the case is different. In testing data some extra words are present. By including those words into the dictionary with the corresponding phoneme sequence will I able to decode those extra words. Is there anything I need to do modification with respect to language model. Please help me. Thanks in advance.