COMBINING AUDIO SAMPLES BY AUTOMATICALLY ADJUSTING SAMPLE CHARACTERISTICS

摘要

A user selects an audio sample to be combined with a set of audio samples. The selected sample is automatically combined with the set of samples based on metadata corresponding to the sample and metadata corresponding to the set of samples. The rhythmic content (beat locations) of the sample and/or set of samples is automatically adjusted to increase rhythmic coherence of the sample and the set of samples, and a pitch of the sample and/or set of samples is automatically adjusted to increase harmonic coherence of the sample and the set of samples. The user is thus able to select a sample and a set of samples, and have one or both automatically adjusted so that the combination sounds good together both rhythmically and harmonically. Audio samples can be similarly combined with other audio samples, and sets of audio samples can be similarly combined with other sets of audio samples.

主权项

1. A method comprising:
receiving user selection of two audio samples including a first audio sample and a second audio sample; obtaining metadata corresponding to the two audio samples, the metadata corresponding to an audio sample describing characteristics of the audio sample; and combining, in response to a user request to combine the samples, the first and second audio samples by automatically adjusting a rhythm of at least one of the first audio sample and the second audio sample to increase rhythmic coherence of the first audio sample and the second audio sample, and automatically adjusting a pitch of at least one of the first audio sample and the second audio sample to increase harmonic coherence of the first audio sample and the second audio sample.