Speech enhancement for noise-robust TTS

Experiments with noisy data

OMLSA: baseline speech enhancement method
RNN-A: RNN enhancement using acoustic-derived features
RNN-AT: RNN enhancement using acoustic- and text-derived features

Natural and vocoded speech samples:

	FEMALE				MALE
	Bus 7.5dB		Cafe 12.5dB		Bus 7.5dB		Cafe 12.5dB
	Natural	Vocoded	Natural	Vocoded	Natural	Vocoded	Natural	Vocoded
CLEAN
NOISY
OMLSA
RNN-A	X		X		X		X
RNN-AT	X		X		X		X

HMM-based synthetic speech samples:

	FEMALE				MALE
	Sample 1	Sample 2	Sample 3	Sample 4	Sample 1	Sample 2	Sample 3	Sample 4
CLEAN
NOISY
OMLSA
RNN-A
RNN-AT