I am building an LSTM to recognize if the person is sad, happy, angry or neutral. This is done by feeding-in his the wave of his voice into the network, as a sequence of bytes (each byte is 0-to-255).
The problem is, my dataset is not large enough, are there efficient ways I could augument my dataset? I am training on short 1.5 second clips and I have 800 of those, which is not enough.
My current augumentation is:
- to add variations in volume
- to add a bit of white noise, which makes it worse :(
Reversing the sequences doesn't seem to be applicable, after all, my network will be predicting non-reversed speech when it's fully trained.