Hi, I understand:
1. Linguistic questions are generated manually or automatically to cluster phones into groups.
2. A binary decision tree is built for each state of a phone (CI phone).
My questions:
1. How do we can build decision trees for a CI phone when it does not have context dependency, e.g: left or right context?
2. Given a 3 state CI phone with 3 decision trees. Do those trees have the same set of linguistic questions for that specific phone? If yes, what is the point to have 3 similar decision trees?
3. Given a 3 state triphone A(B,C). How are decision trees selected from its primary CI phone A?
Last edit: Le Gia Anh Quy 2019-07-25
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
How do we can build decision trees for a CI phone when it does not have context dependency, e.g: left or right context?
We consider all triphones corresponding to that ci phone and build tree with them. So the tree is not for CI phone but for all triphones with CI phone in the middle.
Given a 3 state CI phone with 3 decision trees. Do those trees have the same set of linguistic questions for that specific phone? If yes, what is the point to have 3 similar decision trees?
Questions are always the same, even for different phones. Decisions are different. Trees are different. You can simply open an existing tree file and look inside.
Given a 3 state triphone A(B,C). How are decision trees selected from its primary CI phone A?
Not sure what is the problem, there is only one tree corresponding to the triphone.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi, I understand:
1. Linguistic questions are generated manually or automatically to cluster phones into groups.
2. A binary decision tree is built for each state of a phone (CI phone).
My questions:
1. How do we can build decision trees for a CI phone when it does not have context dependency, e.g: left or right context?
2. Given a 3 state CI phone with 3 decision trees. Do those trees have the same set of linguistic questions for that specific phone? If yes, what is the point to have 3 similar decision trees?
3. Given a 3 state triphone A(B,C). How are decision trees selected from its primary CI phone A?
Last edit: Le Gia Anh Quy 2019-07-25
We consider all triphones corresponding to that ci phone and build tree with them. So the tree is not for CI phone but for all triphones with CI phone in the middle.
Questions are always the same, even for different phones. Decisions are different. Trees are different. You can simply open an existing tree file and look inside.
Not sure what is the problem, there is only one tree corresponding to the triphone.