Give $10, get $10
Introduce a friend to Kadenze. They'll get $10 in Premium membership credit, and you'll get $10 in credit once they sign up for Premium membership.
Read the terms Share your link
Learning Outcomes
• Understanding of the ideas, notation and intuition behind the short-time Fourier Transform (STFT) arguably the most fundamental technique in audio signal processing.
• Understanding of the general concept of a time-frequency representations and how audio features are computed from such representations.
• Ability to discuss how spectral analysis and audio features are used in MIR tasks such as audio classification, tagging, and recommendation.
• Understanding of various types of monophonic pitch detection algorithms based on time-domain, frequency-domain and perceptual modeling.
• Ability to illustrate how pitch detection can be used in applications such as query-by-humming and auto-tuning.
• Understanding of the terminology used to characterize rhythm in music as well as concepts used in rhythm analysis by computers such as onsets, onset strength function, and inter-onset intervals.
• Understanding of the fundamental ideas behind rhythm related MIR tasks such as tempo estimation, beat tracking, rhythm features, swing analysis, and drum transcription.