SBic
extends BaseAlgorithm
in package
SBic
Inputs:
[matrix_real] features - extracted features matrix (rows represent features, and columns represent frames of audio)
Outputs:
[vector_real] segmentation - a list of frame indices that indicate where a segment of audio begins/ends (the indices of the first and last frame are also added to the list at the beginning and end, respectively)
Parameters:
cpw: real ∈ [0,inf) (default = 1.5) complexity penalty weight
inc1: integer ∈ [1,inf) (default = 60) first pass increment [frames]
inc2: integer ∈ [1,inf) (default = 20) second pass increment [frames]
minLength: integer ∈ [1,inf) (default = 10) minimum length of a segment [frames]
size1: integer ∈ [1,inf) (default = 300) first pass window size [frames]
size2: integer ∈ [1,inf) (default = 200) second pass window size [frames]
Description:
This algorithm segments audio using the Bayesian Information Criterion given a matrix of frame features. The algorithm searches homogeneous segments for which the feature vectors have the same probability distribution based on the implementation in [1]. The input matrix is assumed to have features along dim1 (horizontal) while frames along dim2 (vertical).
The segmentation is done in three phases: coarse segmentation, fine segmentation and segment validation. The first phase uses parameters 'size1' and 'inc1' to perform BIC segmentation. The second phase uses parameters 'size2' and 'inc2' to perform a local search for segmentation around the segmentation done by the first phase. Finally, the validation phase verifies that BIC differentials at segmentation points are positive as well as filters out any segments that are smaller than 'minLength'.
Because this algorithm takes as input feature vectors of frames, all units are in terms of frames. For example, if a 44100Hz audio signal is segmented as [0, 99, 199] with a frame size of 1024 and a hopsize of 512, this means, in the time domain, that the audio signal is segmented at [0s, 99512/44100s, 199512/44100s].
An exception is thrown if the input only contains one frame of features (i.e. second dimension is less than 2).
References: [1] Audioseg, http://audioseg.gforge.inria.fr
[2] G. Gravier, M. Betser, and M. Ben, Audio Segmentation Toolkit, release 1.2, 2010. Available online: https://gforge.inria.fr/frs/download.php/25187/audioseg-1.2.pdf
Category: MachineLearning Mode: standard
Table of Contents
Properties
- $algorithmName : string
- $category : string
- $essentia : EssentiaFFI
- $mode : string
- $parameters : array<string|int, mixed>
- $algorithmHandle : CData|null
- $configured : bool
Methods
- __construct() : mixed
- __destruct() : mixed
- compute() : array<string|int, mixed>
- getAlgorithmName() : string
- getCategory() : string
- getMode() : string
- getParameters() : array<string|int, mixed>
- setParameter() : self
- configure() : void
- isValidParameter() : bool
- validateInput() : void
- cleanupAlgorithm() : void
- configureAlgorithmParameters() : void
- estimateOutputSize() : int
- executeAlgorithm() : array<string|int, mixed>
- executeGenericAlgorithm() : array<string|int, mixed>
- executeSpecificAlgorithm() : array<string|int, mixed>
- getAlgorithmCreateFunction() : string
- getValidParameters() : array<string|int, mixed>
- initializeAlgorithm() : void
- prepareInput() : mixed
- processOutput() : array<string|int, mixed>
- processRhythmOutput() : array<string|int, mixed>
- processSpectralOutput() : array<string|int, mixed>
- processStatsOutput() : array<string|int, mixed>
- processTemporalOutput() : array<string|int, mixed>
- processTonalOutput() : array<string|int, mixed>
- setAlgorithmParameter() : void
- setArrayParameter() : void
- validateAlgorithmInput() : void
Properties
$algorithmName
protected
string
$algorithmName
= 'SBic'
$category
protected
string
$category
= 'MachineLearning'
$essentia
protected
EssentiaFFI
$essentia
$mode
protected
string
$mode
= 'standard'
$parameters
protected
array<string|int, mixed>
$parameters
= []
$algorithmHandle
private
CData|null
$algorithmHandle
= null
$configured
private
bool
$configured
= false
Methods
__construct()
public
__construct([array<string|int, mixed> $parameters = [] ]) : mixed
Parameters
- $parameters : array<string|int, mixed> = []
__destruct()
public
__destruct() : mixed
compute()
public
compute(mixed $input) : array<string|int, mixed>
Parameters
- $input : mixed
Return values
array<string|int, mixed>getAlgorithmName()
public
getAlgorithmName() : string
Return values
stringgetCategory()
public
getCategory() : string
Return values
stringgetMode()
public
getMode() : string
Return values
stringgetParameters()
public
getParameters() : array<string|int, mixed>
Return values
array<string|int, mixed>setParameter()
public
setParameter(string $key, mixed $value) : self
Parameters
- $key : string
- $value : mixed
Return values
selfconfigure()
protected
configure(array<string|int, mixed> $parameters) : void
Parameters
- $parameters : array<string|int, mixed>
isValidParameter()
protected
isValidParameter(string $parameter) : bool
Parameters
- $parameter : string
Return values
boolvalidateInput()
protected
validateInput(mixed $input, string $expectedType) : void
Parameters
- $input : mixed
- $expectedType : string
cleanupAlgorithm()
private
cleanupAlgorithm() : void
configureAlgorithmParameters()
private
configureAlgorithmParameters() : void
estimateOutputSize()
private
estimateOutputSize(mixed $input) : int
Parameters
- $input : mixed
Return values
intexecuteAlgorithm()
private
executeAlgorithm(mixed $input) : array<string|int, mixed>
Parameters
- $input : mixed
Return values
array<string|int, mixed>executeGenericAlgorithm()
private
executeGenericAlgorithm(FFI $ffi, mixed $input) : array<string|int, mixed>
Parameters
- $ffi : FFI
- $input : mixed
Return values
array<string|int, mixed>executeSpecificAlgorithm()
private
executeSpecificAlgorithm(FFI $ffi, mixed $input) : array<string|int, mixed>
Parameters
- $ffi : FFI
- $input : mixed
Return values
array<string|int, mixed>getAlgorithmCreateFunction()
private
getAlgorithmCreateFunction() : string
Return values
stringgetValidParameters()
private
getValidParameters() : array<string|int, mixed>
Return values
array<string|int, mixed>initializeAlgorithm()
private
initializeAlgorithm() : void
prepareInput()
private
prepareInput(mixed $input) : mixed
Parameters
- $input : mixed
processOutput()
private
processOutput(array<string|int, mixed> $result) : array<string|int, mixed>
Parameters
- $result : array<string|int, mixed>
Return values
array<string|int, mixed>processRhythmOutput()
private
processRhythmOutput(array<string|int, mixed> $result) : array<string|int, mixed>
Parameters
- $result : array<string|int, mixed>
Return values
array<string|int, mixed>processSpectralOutput()
private
processSpectralOutput(array<string|int, mixed> $result) : array<string|int, mixed>
Parameters
- $result : array<string|int, mixed>
Return values
array<string|int, mixed>processStatsOutput()
private
processStatsOutput(array<string|int, mixed> $result) : array<string|int, mixed>
Parameters
- $result : array<string|int, mixed>
Return values
array<string|int, mixed>processTemporalOutput()
private
processTemporalOutput(array<string|int, mixed> $result) : array<string|int, mixed>
Parameters
- $result : array<string|int, mixed>
Return values
array<string|int, mixed>processTonalOutput()
private
processTonalOutput(array<string|int, mixed> $result) : array<string|int, mixed>
Parameters
- $result : array<string|int, mixed>
Return values
array<string|int, mixed>setAlgorithmParameter()
private
setAlgorithmParameter(FFI $ffi, string $key, mixed $value) : void
Parameters
- $ffi : FFI
- $key : string
- $value : mixed
setArrayParameter()
private
setArrayParameter(FFI $ffi, string $key, array<string|int, mixed> $value) : void
Parameters
- $ffi : FFI
- $key : string
- $value : array<string|int, mixed>
validateAlgorithmInput()
private
validateAlgorithmInput(mixed $input) : void
Parameters
- $input : mixed