Trying to understand what is needed to make HCLG.fst file.
H = the HMM topology,
C = the phone context transducer, converts from monophones to triphones
L = lexicon, phones <--> words
G = grammar, usually represents the ARPA FST.
So, H o C o L o G = HCLG.fst
How do we get H for HCLG.fst ?
The information from it should come from data/lang_chain/topo or data/lang_chain_sp/topo
it is not actually represented as an FST.
How do we get C for HCLG.fst ?
Also C is not represented as a physical FST,
there is a program fstcomposecontext that composes with it programatically
How do we get L for HCLG.fst ?
L.fst can be found in data/lang or data/lang_nosp
How do we get G for HCLG.fst ?
G.carpa can be found in data/lang_test_tglarge or data/lang_nosp_test_fglarge
monophones - just means phone without context
triphones - means a sequence of 3 phones, i.e. left-context/phone/right-context
In linguistics, a triphone is a sequence of three consecutive phonemes.[1] Triphones are useful in models of natural language processing where they are used to establish the various contexts in which a phoneme can occur in a particular natural language.[wikipedia https://en.wikipedia.org/wiki/Triphone]
Comments
Post a Comment