Preprocessing Audio & Music Data
Related fields are Music Information
Retrieval and
Computer Music.
Features
- Segmentation - the process of separating the audio stream into segments with certain
properties.
- Automatic Music
Transcription
- Extracting musical notes from audio
- Frequency domain via Fourier transform
- Wavelet transform
- Mel-frequency cepstral coefficients
MFCC
details
- Basic statistics: Mean, Variance, Skewness,
ZCR, RMS, Spectral Centroid, Spectral Irregularity, Spectral Flatness,
Spectral Tonality, Spectral Crest, Spectral Slope, Spectral Rolloff, Spectral
Loudness, Spectral Pitch, Harmonic Odd Even Ratio, and Bark Scale
- Getting Started with Audio Data Analysis using Deep
Learning (with case study)
Important Papers
G. Hinton et al., “Deep Neural Networks for Acoustic Modeling in Speech
Recognition: The Shared Views of Four Research Groups,” in IEEE Signal
Processing Magazine, vol. 29, no. 6, pp. 82-97, Nov. 2012.
doi: 10.1109/MSP.2012.2205597
Software Packages