HCLG
L.fst: The Phonetic Dictionary FST
L?maps monophone sequences to words.
The file L.fst is the Finite State Transducer form of the lexicon with phone symbols on the input and word symbols on the output.
L_disambig.fst:The Phonetic Dictionary with Disambiguation Symbols FST
A lexicon with disambiguation symbols
FSA grammar (can be built from an n-gram grammar).
C maps triphone sequences to monophones.
Expands the phones into context-dependent phones.
H maps multiple HMM states (a.k.a. transition-ids in Kaldi-speak) to context-dependent triphones.
Expands out the HMMs. On the right are the context-dependent phones and on the left are the pdf-ids.?
HCLG.fst: final graph
總結(jié)一下:
構(gòu)圖過(guò)程 G -> L -> C -> H
?G: 作為 acceptor (輸入?symbol?與輸出相同)菩鲜,用于對(duì)grammar 或者 language model進(jìn)行編碼
?L:Lexicon, 其輸出 symbol?是 words, 輸入 symbol?是 phones
?C:context-dependency其輸出 symbol 是 phones, 其輸入?symbol 為表示context-dependencyphones
?H: 包括HMM?definitions,其輸出 symbol 為context-dependencyphones, 其輸入 symbol 為transitions-ids(即 對(duì) pdf-id 和 其它信息編碼后的 id)