DYNAMICALLY ADAPTED PITCH CORRECTION BASED ON AUDIO INPUT

摘要

Systems and methods for adjusting pitch of an audio signal include detecting input notes in the audio signal, mapping the input notes to corresponding output notes, each output note having an associated upper note boundary and lower note boundary, and modifying at least one of the upper note boundary and the lower note boundary of at least one output note in response to previously received input notes. Pitch of the input notes may be shifted to match an associated pitch of corresponding output notes. Delay of the pitch shifting process may be dynamically adjusted based on detected stability of the input notes.

主权项

1. A method for processing a vocal signal and a non-vocal signal, comprising:
detecting vocal input notes in the vocal signal; generating a vocal input note likelihood of occurrence based on number of occurrences of each detected vocal input note; detecting non-vocal input notes in the non-vocal signal; generating a non-vocal note likelihood of occurrence based on number of occurrences of each detected non-vocal input note; combining the vocal note likelihood of occurrence and non-vocal note likelihood of occurrence to generate a combined note likelihood of occurrence; mapping the vocal input notes to corresponding vocal output notes based on associated upper and lower note boundaries; shifting pitch of the vocal input notes to a pitch associated with the corresponding vocal output notes; and adjusting the upper and lower note boundaries in response to the combined note likelihood of occurrence.