java audio embedding

java-audio-embedding

Penyematan audio di Java

Proyek saat ini mencoba mengembangkan encoder audio Java murni yang dapat digunakan dalam program Java atau Android murni. Encoder audio semacam itu dapat digunakan untuk klasifikasi genre musik atau pencarian musik, atau rekomendasi musik.

Proyek saat ini berisi dua jaringan pembelajaran mendalam yang diadopsi dari:

• jaringan ulang
• cifar

Pelatihan dan validasi kedua model ini ditunjukkan di bawah ini:

Penggunaan

Latih pengklasifikasi audio di Keras

Paket pembelajaran mesin di Java adalah tensorflow, yang memuat model pengklasifikasi audio terlatih (format .pb). Model pengklasifikasi audio awalnya diimplementasikan dan dilatih menggunakan Keras dengan Python. Model pengklasifikasi terlatih ini (dalam format .h5) kemudian diubah menjadi file model .pb yang dapat langsung dimuat oleh tensorflow di Java.

Pelatihan keras model pengklasifikasi audio dapat ditemukan di README_Training.md

Jalankan pengklasifikasi audio di Java

Contoh kode di bawah ini menunjukkan cara menggunakan pengklasifikasi audio cifar untuk memprediksi genre musik:

 import com . github . chen0040 . tensorflow . classifiers . models . cifar10 . Cifar10AudioClassifier ;
import com . github . chen0040 . tensorflow . classifiers . utils . ResourceUtils ;
import org . slf4j . Logger ;
import org . slf4j . LoggerFactory ;

import java . io . File ;
import java . io . IOException ;
import java . io . InputStream ;
import java . util . ArrayList ;
import java . util . Collections ;
import java . util . List ;

public class Demo {
    public static void main ( String [] args ) {
        InputStream inputStream = ResourceUtils . getInputStream ( "tf_models/cifar10.pb" );
        Cifar10AudioClassifier classifier = new Cifar10AudioClassifier ();
        classifier . load_model ( inputStream );
        
        List < String > paths = getAudioFiles ();
        
        Collections . shuffle ( paths );
        
        for ( String path : paths ) {
            System . out . println ( "Predicting " + path + " ..." );
            File f = new File ( path );
            String label = classifier . predict_audio ( f );
        
            System . out . println ( "Predicted: " + label );
        }
    }
}

Contoh kode di bawah ini menunjukkan cara menggunakan pengklasifikasi audio resnet v2 untuk memprediksi genre musik:

 import com . github . chen0040 . tensorflow . classifiers . resnet_v2 . ResNetV2AudioClassifier ;
import com . github . chen0040 . tensorflow . classifiers . utils . ResourceUtils ;
import org . slf4j . Logger ;
import org . slf4j . LoggerFactory ;

import java . io . File ;
import java . io . IOException ;
import java . io . InputStream ;
import java . util . ArrayList ;
import java . util . Collections ;
import java . util . List ;

public class Demo {
    public static void main ( String [] args ) {
        InputStream inputStream = ResourceUtils . getInputStream ( "tf_models/resnet-v2.pb" );
        ResNetV2AudioClassifier classifier = new ResNetV2AudioClassifier ();
        classifier . load_model ( inputStream );
        
        List < String > paths = getAudioFiles ();
        
        Collections . shuffle ( paths );
        
        for ( String path : paths ) {
            System . out . println ( "Predicting " + path + " ..." );
            File f = new File ( path );
            String label = classifier . predict_audio ( f );
        
            System . out . println ( "Predicted: " + label );
        }
    }
}

Ekstrak fitur dari audio di Java

Contoh kode di bawah ini menunjukkan cara menggunakan pengklasifikasi audio cifar untuk menyandikan file audio ke dalam array float:

 import com . github . chen0040 . tensorflow . classifiers . models . cifar10 . Cifar10AudioClassifier ;
import com . github . chen0040 . tensorflow . classifiers . utils . ResourceUtils ;
import org . slf4j . Logger ;
import org . slf4j . LoggerFactory ;

import java . io . File ;
import java . io . IOException ;
import java . io . InputStream ;
import java . util . ArrayList ;
import java . util . Collections ;
import java . util . List ;

public class Demo {
    public static void main ( String [] args ){
        InputStream inputStream = ResourceUtils . getInputStream ( "tf_models/cifar10.pb" );
        Cifar10AudioClassifier classifier = new Cifar10AudioClassifier ();
        classifier . load_model ( inputStream );
        
        List < String > paths = getAudioFiles ();
        
        Collections . shuffle ( paths );
        
        for ( String path : paths ) {
            System . out . println ( "Encoding " + path + " ..." );
            File f = new File ( path );
            float [] encoded_audio = classifier . encode_audio ( f );
        
            System . out . println ( "Encoded: " + Arrays . toString ( encoded_audio ));
        }
    }
}

Contoh kode di bawah ini menunjukkan cara pengklasifikasi audio resnet v2 untuk menyandikan file audio ke dalam array float:

 import com . github . chen0040 . tensorflow . classifiers . resnet_v2 . ResNetV2AudioClassifier ;
import com . github . chen0040 . tensorflow . classifiers . utils . ResourceUtils ;
import org . slf4j . Logger ;
import org . slf4j . LoggerFactory ;

import java . io . File ;
import java . io . IOException ;
import java . io . InputStream ;
import java . util . ArrayList ;
import java . util . Collections ;
import java . util . List ;

public class Demo {
    public static void main ( String [] args ) {
        InputStream inputStream = ResourceUtils . getInputStream ( "tf_models/resnet-v2.pb" );
        ResNetV2AudioClassifier classifier = new ResNetV2AudioClassifier ();
        classifier . load_model ( inputStream );
        
        List < String > paths = getAudioFiles ();
        
        Collections . shuffle ( paths );
        
        for ( String path : paths ) {
            System . out . println ( "Encoding " + path + " ..." );
            File f = new File ( path );
            float [] encoded_audio = classifier . encode_audio ( f );
        
            System . out . println ( "Encoded: " + Arrays . toString ( encoded_audio ));
        }
    }
}

Mesin Pencari Audio

Contoh kode di bawah ini menunjukkan cara mengindeks dan mencari file audio menggunakan kelas AudioSearchEngine:

 import com . github . chen0040 . tensorflow . search . models . AudioSearchEngine ;
import com . github . chen0040 . tensorflow . search . models . AudioSearchEntry ;

import java . io . File ;
import java . util . List ;

public class Demo {
    public static void main ( String [] args ){
        AudioSearchEngine searchEngine = new AudioSearchEngine ();
        if (! searchEngine . loadIndexDbIfExists ()) {
            searchEngine . indexAll ( FileUtils . getAudioFiles ());
            searchEngine . saveIndexDb ();
        }
        
        int pageIndex = 0 ;
        int pageSize = 20 ;
        boolean skipPerfectMatch = true ;
        File f = new File ( "mp3_samples/example.mp3" );
        System . out . println ( "querying similar music to " + f . getName ());
        List < AudioSearchEntry > result = searchEngine . query ( f , pageIndex , pageSize , skipPerfectMatch );
        for ( int i = 0 ; i < result . size (); ++ i ){
            System . out . println ( "# " + i + ": " + result . get ( i ). getPath () + " (distSq: " + result . get ( i ). getDistance () + ")" );
        }
    }
}

Rekomendasi Musik

Contoh kode di bawah ini menunjukkan cara merekomendasikan musik berdasarkan riwayat musik pengguna menggunakan kelas KnnAudioRecommender:

 import com . github . chen0040 . tensorflow . classifiers . utils . FileUtils ;
import com . github . chen0040 . tensorflow . recommenders . models . AudioUserHistory ;
import com . github . chen0040 . tensorflow . recommenders . models . KnnAudioRecommender ;
import com . github . chen0040 . tensorflow . search . models . AudioSearchEntry ;

import java . io . File ;
import java . util . Collections ;
import java . util . List ;

public class Demo {
    public static void main ( String [] args ){
        AudioUserHistory userHistory = new AudioUserHistory ();
        
        List < String > audioFiles = FileUtils . getAudioFilePaths ();
        Collections . shuffle ( audioFiles );
        
        for ( int i = 0 ; i < 40 ; ++ i ){
            String filePath = audioFiles . get ( i );
            userHistory . logAudio ( filePath );
            try {
                Thread . sleep ( 100L );
            } catch ( InterruptedException e ) {
                e . printStackTrace ();
            }
        }
        
        KnnAudioRecommender recommender = new KnnAudioRecommender ();
        if (! recommender . loadIndexDbIfExists ()) {
            recommender . indexAll ( new File ( "music_samples" ). listFiles ( a -> a . getAbsolutePath (). toLowerCase (). endsWith ( ".au" )));
            recommender . saveIndexDb ();
        }
        
        System . out . println ( userHistory . head ( 10 ));
        
        int k = 10 ;
        List < AudioSearchEntry > result = recommender . recommends ( userHistory . getHistory (), k );
        
        for ( int i = 0 ; i < result . size (); ++ i ){
            AudioSearchEntry entry = result . get ( i );
            System . out . println ( "Search Result #" + ( i + 1 ) + ": " + entry . getPath ());
        }
    }
}