2. Sound Feature
Sound features can be used to detect speakers, detect the
gender, the age, diseases and much more through the voice.
3. Energy
The energy of a signal is the total magnitude of the signal,
i.e. how loud the signal is(Can use it as a classifier if
someone anger or not..
. It is defined as:
[E(x) = sum_n {mid x(n) mid}^2]
4. Tempo
(BPM).
An estimate of the tempo in Beats Per Minute:
the rate of speed of a musical piece or passage .
Like a heartbeat, it can also be thought of as the 'pulse' of
the music. Tempo is measured in BPM, or beats pe
-can indicate that someone are arrested.
5. Zero Crossing Rate
The zero-crossing rate (ZCR) is the rate at which a signal
changes from positive to zero to negative or from negative to
zero to positive. Its value has been widely used in both
speech recognition and music information retrieval, being a
key feature to classify percussive sounds. is an indicator
function.
6.
7. Spectrogram
Ever heard of a spectrogram? It’s a 2D plot between time and
frequency where each point in the plot represents the
amplitude of a particular frequency at a particular time in
terms of intensity of color. In simple terms, the spectrogram
is a spectrum (broad range of colors) of frequencies as it
varies with time.
8.
9. Spectral Centroid
The spectral centroid is a measure used in
digital signal processing to characterise a
spectrum. It indicates where the center of mass
of the spectrum is located. Perceptually, it has a
robust connection with the impression of
brightness of a sound.
10. Spectral Centroid
The spectral centroid is a measure that
indicates where the “center of mass” of the
spectrum is. Perceptually, it has a robust
connection with the impression of “brightness”
of a sound, and therefore is used to
characterise musical timbre.