training allows us to generate an acoustic model which is modeled with HMM, theoretically I want to know exactly how is modeling either word by word or sentence by sentence or phone by phone. And also the acoustic model provides for each HMM model its own acoustic vectors or what?
Last edit: ElMokhtar Ahmed 2015-08-30
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
training allows us to generate an acoustic model which is modeled with HMM, theoretically I want to know exactly how is modeling either word by word or sentence by sentence or phone by phone. And also the acoustic model provides for each HMM model its own acoustic vectors or what?
Last edit: ElMokhtar Ahmed 2015-08-30
You can read about it in a text book
Spoken Language Processing
http://www.amazon.com/Spoken-Language-Processing-Algorithm-Development/dp/0130226165