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 (Since R2019a)
audioDeltaCompute delta features (Since R2020b)
cepstralCoefficientsExtract cepstral coefficients (Since R2020b)
gtccExtract gammatone cepstral coefficients, log-energy, delta, and delta-delta (Since R2019a)
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 (Since R2019a)
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 (Since R2019a)
spectralCrestSpectral crest for audio signals and auditory spectrograms (Since R2019a)
spectralDecreaseSpectral decrease for audio signals and auditory spectrograms (Since R2019a)
spectralEntropySpectral entropy for audio signals and auditory spectrograms (Since R2019a)
spectralFlatnessSpectral flatness for audio signals and auditory spectrograms (Since R2019a)
spectralFluxSpectral flux for audio signals and auditory spectrograms (Since R2019a)
spectralKurtosisSpectral kurtosis for audio signals and auditory spectrograms (Since R2019a)
spectralRolloffPointSpectral rolloff point for audio signals and auditory spectrograms (Since R2019a)
spectralSkewnessSpectral skewness for audio signals and auditory spectrograms (Since R2019a)
spectralSlopeSpectral slope for audio signals and auditory spectrograms (Since R2019a)
spectralSpreadSpectral spread for audio signals and auditory spectrograms (Since R2019a)
erb2hzConvert from equivalent rectangular bandwidth (ERB) scale to hertz (Since R2019a)
bark2hzConvert from Bark scale to hertz (Since R2019a)
mel2hzConvert from mel scale to hertz (Since R2019a)
hz2erbConvert from hertz to equivalent rectangular bandwidth (ERB) scale (Since R2019a)
hz2barkConvert from hertz to Bark scale (Since R2019a)
hz2melConvert from hertz to mel scale (Since R2019a)
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