Mpeg7 audio feature
在頻率上級時間上共有17種描述,分成六個群組:
Timbral Temporal,Timbral Spectral,Basic Spectral,Basic,
Signal Parameters,Spectral Basic。
下面採用前三種。
two timbral temporal feature:
Log Attack Time (LAT)
Temporal Centroid (TC)
four basic spectral time-freqency amalysis:
Audio Spectral Envelope (ASE)
Audio Spectral Centroid (ASC)
Audio Spectral Spread (ASS)
Audio Spectral Flatness (ASF)
five timbral spectral feature:
Spectral Centroid (SC)
Harmonic Spectral Centroid (HSC)
Harmonic Spectral Deviation (HSD)
Harmonic Spectral Spread (HSS)
Harmonic Spectral Variation (HSV)
other
Linear Predictive Coding (LPC)
Mel-scale Freqency Ceptral Coefficient (MFCC)
Zero-Crossing Rate (ZCR)
Pitch
Sound Pressure Level (SPL)
Autocorrelation
Skewness
Kurtosis
Timbral Temporal,Timbral Spectral,Basic Spectral,Basic,
Signal Parameters,Spectral Basic。
下面採用前三種。
two timbral temporal feature:
Log Attack Time (LAT)
Temporal Centroid (TC)
four basic spectral time-freqency amalysis:
Audio Spectral Envelope (ASE)
Audio Spectral Centroid (ASC)
Audio Spectral Spread (ASS)
Audio Spectral Flatness (ASF)
five timbral spectral feature:
Spectral Centroid (SC)
Harmonic Spectral Centroid (HSC)
Harmonic Spectral Deviation (HSD)
Harmonic Spectral Spread (HSS)
Harmonic Spectral Variation (HSV)
other
Linear Predictive Coding (LPC)
Mel-scale Freqency Ceptral Coefficient (MFCC)
Zero-Crossing Rate (ZCR)
Pitch
Sound Pressure Level (SPL)
Autocorrelation
Skewness
Kurtosis
留言
張貼留言