speech-scoring/TODO.md

0. generate the samples of phoneme similarity variants.
1. create spectrograms of 150ms windows with 50ms overlap for each word.
2. train a rnn to output a vector using the spectrograms
3. train a nn to output True/False based on the acceptability of the rnn output. -> Siamese network(implementation detail)
4. validate with real world samples
1. implemented spectrogram generator for audio files 2. imported siamese network class (wip) 3. added similarity measure based phoneme neighbor generator 4. fixed samplegen variants code 5. create triplets (wip) 6. updates 2017-10-13 11:10:57 +00:00			`0. generate the samples of phoneme similarity variants.`
			`1. create spectrograms of 150ms windows with 50ms overlap for each word.`
			`2. train a rnn to output a vector using the spectrograms`
			`3. train a nn to output True/False based on the acceptability of the rnn output. -> Siamese network(implementation detail)`
discarding phoneme incapable synthesizers 2017-10-26 11:21:32 +00:00			`4. validate with real world samples`