Number of source estimation knowledge sources¶
This section focuses on implementation of knowledge sources for the estimation of active sound sourcs in an auditory scene within the blackboard framework.
Number of Sources knowledge source: NumberOfsourcesKS
¶
Objects of class NumberOfsourcesKS
implement models, by incorporating
an instance of a model (which has to implement the models.Base
interface) with knowledge about the relationship of auditory cues and the number of active sound sources.
The model gets loaded from directories you specify upon construction, and should be created with the
Estimating the Number of Sound Sources. The model object of NumberOfsourcesKS
can
employ any kind of model, such as a linear support vector machine, or a Gaussian
mixture model. The NumberOfsourcesKS
needs access to Auditory front-end signals, thus it is a
subclass of AuditoryFrontEndDepKS
(see
Section Auditory signal dependent knowledge source superclass: AuditoryFrontEndDepKS). The model object holds the signal
request structure.
The knowledge source predicts, based on the incorporated source model the number of active sound sources in the currently received auditory stream.
binds to | AuditoryFrontEndKS.KsFiredEvent |
reads data category | locationHypothesis (otherwise sourcesAzimuthsDistributionHypotheses )
possible also identityHypotheses if required by the model’s feature creator
(see :ref:sec-amlttp-select-features) |
writes data category | NumberOfSourcesHypotheses |
triggers event | KsFiredEvent |