Learn R Programming

seewave (version 2.1.8)

simspec: Similarity between two frequency spectra

Description

This function estimates the similarity between two frequency spectra.

Usage

simspec(spec1, spec2, f = NULL, mel = FALSE,
norm = FALSE, PMF = FALSE,
plot = FALSE, type = "l",
lty =c(1, 2, 3), col = c(2, 4, 1),
flab = NULL, alab = "Amplitude (percentage)",
flim = NULL, alim = NULL,
title = TRUE, legend = TRUE, ...)

Arguments

spec1

a first data set resulting of a spectral analysis obtained with spec or meanspec (not in dB). This can be either a two-column matrix (col1 = frequency, col2 = amplitude) or a vector (amplitude).

spec2

a first data set resulting of a spectral analysis obtained with spec or meanspec (not in dB). This can be either a two-column matrix (col1 = frequency, col2 = amplitude) or a vector (amplitude).

f

sampling frequency of waves used to obtain spec1 and spec2 (in Hz). Not necessary if spec1 and/or spec2 is a two columns matrix obtained with spec or meanspec.

mel

a logical, if TRUE the (htk-)mel scale is used.

norm

a logical, if TRUE spec1 and spec2 are normalised (scaled) between 0 and 1.

PMF

a logical, if TRUE spec1 and spec2 are transformed into probability mass functions.

plot

logical, if TRUE plots both spectra and similarity function (by default FALSE).

type

if plot is TRUE, type of plot that should be drawn. See plot for details (by default "l" for lines).

lty

a vector of length 3 for the line type of spec1, spec2 and of the similarity function if type="l".

col

a vector of length 3 for the colour of spec1, spec2, and the similarity function.

flab

title of the frequency axis.

alab

title of the amplitude axis.

flim

the range of frequency values.

alim

range of amplitude axis.

title

logical, if TRUE, adds a title with S value.

legend

logical, if TRUE adds a legend to the plot.

other plot graphical parameters.

Value

The similarity index is returned. This value is in %. When plot is TRUE, both spectra and the similarity function are plotted on the same graph. The similarity index is the mean of this function.

Details

Spectra similarity is assessed according to: $$S = \frac{100/N} \times{\sum_{i=1}^N{\frac{\min{spec1(i),spec2(i)}} {\max{spec1(i),spec2(i)}}}}$$ with S in %.

References

Deecke, V. B. and Janik, V. M. 2006. Automated categorization of bioacoustic signals: avoiding perceptual pitfalls. Journal of the Acoustical Society of America, 119: 645-653.

See Also

spec, meanspec, corspec, diffspec, diffenv, kl.dist, ks.dist, logspec.dist, itakura.dist

Examples

Run this code
# NOT RUN {
a<-noisew(f=8000,d=1)
b<-synth(f=8000,d=1,cf=2000)
c<-synth(f=8000,d=1,cf=1000)
d<-noisew(f=8000,d=1)
speca<-spec(a,f=8000,at=0.5,plot=FALSE)
specb<-spec(b,f=8000,at=0.5,plot=FALSE)
specc<-spec(c,f=8000,at=0.5,plot=FALSE)
specd<-spec(d,f=8000,at=0.5,plot=FALSE)
simspec(speca,speca)
simspec(speca,specb)
simspec(speca,specc,plot=TRUE)
simspec(specb,specc,plot=TRUE)
#[1] 12.05652
simspec(speca,specd,plot=TRUE)
## mel scale
require(tuneR)
data(orni)
data(tico)
orni.mel <- melfcc(orni, nbands = 256, dcttype = "t3", fbtype = "htkmel", spec_out=TRUE)
orni.mel.mean <- apply(orni.mel$aspectrum, MARGIN=2, FUN=mean)
tico.mel <- melfcc(tico, nbands = 256, dcttype = "t3", fbtype = "htkmel", spec_out=TRUE)
tico.mel.mean <- apply(tico.mel$aspectrum, MARGIN=2, FUN=mean)
simspec(orni.mel.mean, tico.mel.mean, f=22050, mel=TRUE, plot=TRUE)
# }

Run the code above in your browser using DataLab