Main Content

Feature Extraction

Mel spectrogram, MFCC, pitch, spectral descriptors

Extract features from audio signals for use as input to machine learning or deep learning systems. Use individual functions, such as melSpectrogram, mfcc, pitch, and spectralCentroid, or use the audioFeatureExtractor object to create a feature extraction pipeline that minimizes redundant calculations. Use blocks such as Mel Spectrogram and MFCC to extract features from audio signals in Simulink®. In live scripts, use Extract Audio Features to graphically select the features to extract.

Objects

audioFeatureExtractorStreamline audio feature extraction (Since R2019b)
ivectorSystemCreate i-vector system (Since R2021a)

Live Editor Tasks

Extract Audio FeaturesStreamline audio feature extraction in the Live Editor (Since R2020a)

Functions

expand all

audioDeltaCompute delta features (Since R2020b)
designAuditoryFilterBankDesign auditory filter bank (Since R2019b)
melSpectrogramMel spectrogram
audioDeltaCompute delta features (Since R2020b)
cepstralCoefficientsExtract cepstral coefficients (Since R2020b)
gtccExtract gammatone cepstral coefficients, log-energy, delta, and delta-delta
mfccExtract MFCC, log energy, delta, and delta-delta of audio signal
openl3EmbeddingsExtract OpenL3 feature embeddings (Since R2022a)
vggishEmbeddingsExtract VGGish feature embeddings (Since R2022a)
audioDeltaCompute delta features (Since R2020b)
harmonicRatioHarmonic ratio
pitchEstimate fundamental frequency of audio signal
pitchnnEstimate pitch with deep learning neural network (Since R2021a)
audioDeltaCompute delta features (Since R2020b)
spectralCentroidSpectral centroid for audio signals and auditory spectrograms
spectralCrestSpectral crest for signals and spectrograms
spectralDecreaseSpectral decrease for audio signals and auditory spectrograms
spectralEntropySpectral entropy for signals and spectrograms
spectralFlatnessSpectral flatness for signals and spectrograms
spectralFluxSpectral flux for audio signals and auditory spectrograms
spectralKurtosisSpectral kurtosis for signals and spectrograms
spectralRolloffPointSpectral rolloff point for audio signals and auditory spectrograms
spectralSkewnessSpectral skewness for signals and spectrograms
spectralSlopeSpectral slope for audio signals and auditory spectrograms
spectralSpreadSpectral spread for audio signals and auditory spectrograms
erb2hzConvert from equivalent rectangular bandwidth (ERB) scale to hertz
bark2hzConvert from Bark scale to hertz
mel2hzConvert from mel scale to hertz
hz2erbConvert from hertz to equivalent rectangular bandwidth (ERB) scale
hz2barkConvert from hertz to Bark scale
hz2melConvert from hertz to mel scale
phon2soneConvert from phon to sone (Since R2020a)
sone2phonConvert from sone to phon (Since R2020a)

Blocks

Audio DeltaCompute delta features (Since R2022b)
Auditory SpectrogramExtract mel, Bark, or ERB spectrogram from audio (Since R2022a)
Cepstral CoefficientsExtract cepstral coefficients from spectrogram (Since R2022b)
Design Auditory Filter BankDesign frequency-domain auditory filter bank (Since R2022a)
Design Mel Filter BankDesign frequency-domain mel filter bank (Since R2022a)
Mel SpectrogramExtract mel spectrogram from audio (Since R2022a)
MFCCExtract mel-frequency cepstral coefficients from audio (Since R2022b)

Topics