org.openimaj.demos.sandbox.audio

Class AudioClassifier<ANNOTATION>

java.lang.Object

org.openimaj.ml.annotation.AbstractAnnotator<SampleBuffer,ANNOTATION>

org.openimaj.demos.sandbox.audio.AudioClassifier<ANNOTATION>

Type Parameters:

ANNOTATION - The annotation type

All Implemented Interfaces:

Classifier<ANNOTATION,SampleBuffer>, Annotator<SampleBuffer,ANNOTATION>

public class AudioClassifier<ANNOTATION>
extends AbstractAnnotator<SampleBuffer,ANNOTATION>

A general audio classifier class that can use any annotator and any dataset. The AudioClassifier requires an annotator to be passed in, which in turn requires feature extractor. The feature extractor must be able to extract a FeatureVector from a SampleBuffer.

The train(List) method takes a list of pairs, where the pairs are streams mapped to annotations. Each stream represents a set of SampleBuffers for that annotation. They are extracted into AnnotatedObjects before being passed into the annotator for feature extraction.

Version:

$Author$, $Revision$, $Date$

Author:

David Dupplaw (dpd@ecs.soton.ac.uk)

Constructor Summary

Constructors

Constructor and Description
AudioClassifier(BatchAnnotator<SampleBuffer,ANNOTATION> annotator) Constructor that takes the actual annotator type to use.

Method Summary

Modifier and Type	Method and Description
List<ScoredAnnotation<ANNOTATION>>	annotate(SampleBuffer object) Generate annotations for the given object.
Set<ANNOTATION>	getAnnotations()
void	train(List<IndependentPair<AudioStream,ANNOTATION>> streams) Train the annotator on the given streams.

Methods inherited from class org.openimaj.ml.annotation.AbstractAnnotator

classify

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

AudioClassifier

public AudioClassifier(BatchAnnotator<SampleBuffer,ANNOTATION> annotator)

Constructor that takes the actual annotator type to use.

Parameters:

annotator - The annotator

Method Detail

train

public void train(List<IndependentPair<AudioStream,ANNOTATION>> streams)

Train the annotator on the given streams. The streams are annotated with the appropriate annotation, and sample chunks (and therefore buffers) are gathered from the streams into batches to train the annotator.

Parameters:

streams - The annotated streams

getAnnotations

public Set<ANNOTATION> getAnnotations()

Returns:

a Set of all annotations this Annotator knows about

See Also:

Annotator.getAnnotations()

annotate

public List<ScoredAnnotation<ANNOTATION>> annotate(SampleBuffer object)

Generate annotations for the given object.

Parameters:

object - the image

Returns:

generated annotations

See Also:

Annotator.annotate(java.lang.Object)