when WITH_SHORT_PAUSES = 1

georgid / AlignmentDuration

Lyrics-to-audio-alignement system. Based on Machine Learning Algorithms: Hidden Markov Models with Viterbi forced alignment. The alignment is explicitly aware of durations of musical notes. The phonetic model are classified with MLP Deep Neural Network.

http://mtg.upf.edu/node/3751

GNU Affero General Public License v3.0

56 stars 6 forks source link

when WITH_SHORT_PAUSES = 1 #36

Open georgid opened 8 years ago

georgid commented 8 years ago

we got error: last state for word SAZ is not sp. Sorry - not implemented.

The problem is it is that I removed sp from SAZ so that it is not sil sp but sil.

georgid commented 8 years ago

remove align._PhonemeBase.PhonemeBase.getNumStates and replace by return 1

move this logic ```

   stateIndices = range( phoneme.getNumStates())   
        if ParametersAlgo.ONLY_MIDDLE_STATE and len(phoneme.model.states) == 3: # take only middle state. 1 is middle in 0,1,2
                 stateIndices = [1]


from align._LyricsWithModelsBase._LyricsWithModelsBase._phonemes2stateNetwork
to align._LyricsWithModelsBase._LyricsWithModelsBase._createStateWithDur