Est. Budget: $2,000.00
Looking for someone with knowledge in machine learning and audio processing to build software that would be capable of learning human voices from samples fed to it. After learning the samples, the application should be able to, in real time, convert any streaming vocal audio input to sound similar to the learned samples.
1) application is fed one or several audio files (whatever minimum amount is required).
2) application processes the audio and creates some sort of permanently ...