Create sound encoders

[breznak]

Greetings guys,

I'm happy I can hop on audio and play for some time with this repo! My question is about encoders and ease of use of this repo, would you be in for extracting the code from your examples and creating reusable encoders in NuPIC style? So this repo could be pip-installed (like nupic.vision) and provide the encoders and examples for new users who need to use sound with HTM (currently me :P)

From what I saw in the codebase the encoders could be:

• [ ] {MIDI/WAV/MP3}toScalar{Adaptive,RDSE,ScalarEncoder}
  • [x] WAV (with scipy backend) encoder
  • [ ] MIDI encoder
• [ ] SoundToSpiketrain(Cochlea)Encoder
  • see https://github.com/mrkrd/cochlea
• [ ] any other state of the art models?
• [ ] Experiments could reuse the encoders

Blocked by: pip #24 (partially blocked)

[breznak]

Guys, I have a PR for WAV encoder, what other sound formats are you using in the experiments? Would be cool if we could extract any format-specific functionality for parsing the files in here into encoders, and your experiments would simply call the SoundEncoder :sunglasses:

[rhyolight]

I've only used WAV so far. I want to find some time to use this encoder, but so busy lately 😫

[breznak]

@passiweinberger next is the MIDI encoder, could you point me to the code how you transform and work with it?