Summary/Goals
This project aims to do a real-time audio note recognition software for monophonic signals (like solos).The input must be a monophonic wave signal (only one voice, with one melodic instrument). The result are MIDI events launched trough the ALSA sequencer. (recognized notes are printed to the standard output too)
Limits
- Latency: currently around 150ms
- Human voices are badly supported: not for some complexity criteria, but for unprecision of the pitch. A human voice is more easily "false" than an instrument. A better recognition would recognize pitch differences and not absolute pitch, and so be more "human tolerant"
Current features
- Pitch recognition (has absolute note, without following exactly the emited note)
- Real-time recognition
- ALSA support
- JACK support
Current work
- bubble algo
- Volume recognition
Futur works
- Pitch effects
- see the TODO file