public override double GetDistance(AudioFeature f, AudioFeature.DistanceType t)
{
if (!(f is Scms))
{
new Exception("Can only handle AudioFeatures of type Scms, not of: " + f);
return(-1);
}
Scms other = (Scms)f;
DistanceMeasure distanceMeasure = DistanceMeasure.Euclidean;
switch (t)
{
case AudioFeature.DistanceType.Dtw_Euclidean:
distanceMeasure = DistanceMeasure.Euclidean;
break;
case AudioFeature.DistanceType.Dtw_SquaredEuclidean:
distanceMeasure = DistanceMeasure.SquaredEuclidean;
break;
case AudioFeature.DistanceType.Dtw_Manhattan:
distanceMeasure = DistanceMeasure.Manhattan;
break;
case AudioFeature.DistanceType.Dtw_Maximum:
distanceMeasure = DistanceMeasure.Maximum;
break;
case AudioFeature.DistanceType.UCR_Dtw:
return(UCRCSharp.UCR.DTW(this.GetArray(), other.GetArray()));
case AudioFeature.DistanceType.CosineSimilarity:
return(CosineSimilarity(this, other));
case AudioFeature.DistanceType.BitStringHamming:
return(Imghash.ImagePHash.HammingDistance(this.BitString, other.BitString));
case AudioFeature.DistanceType.KullbackLeiblerDivergence:
default:
return(Distance(this, other, new ScmsConfiguration(Analyzer.MFCC_COEFFICIENTS)));
}
Dtw dtw = new Dtw(this.GetArray(), other.GetArray(), distanceMeasure, true, true, null, null, null);
return(dtw.GetCost());
}
/// <summary>Get Distance</summary>
/// <seealso cref="">comirva.audio.feature.AudioFeature#GetDistance(comirva.audio.feature.AudioFeature)</seealso>
public override double GetDistance(AudioFeature f, AudioFeature.DistanceType t)
{
if (!(f is MandelEllis))
{
new Exception("Can only handle AudioFeatures of type Mandel Ellis, not of: " + f);
return(-1);
}
MandelEllis other = (MandelEllis)f;
DistanceMeasure distanceMeasure = DistanceMeasure.Euclidean;
switch (t)
{
case AudioFeature.DistanceType.Dtw_Euclidean:
distanceMeasure = DistanceMeasure.Euclidean;
break;
case AudioFeature.DistanceType.Dtw_SquaredEuclidean:
distanceMeasure = DistanceMeasure.SquaredEuclidean;
break;
case AudioFeature.DistanceType.Dtw_Manhattan:
distanceMeasure = DistanceMeasure.Manhattan;
break;
case AudioFeature.DistanceType.Dtw_Maximum:
distanceMeasure = DistanceMeasure.Maximum;
break;
case AudioFeature.DistanceType.KullbackLeiblerDivergence:
default:
return(KullbackLeibler(this.gmmMe, other.gmmMe) + KullbackLeibler(other.gmmMe, this.gmmMe));
}
Dtw dtw = new Dtw(this.GetArray(), other.GetArray(), distanceMeasure, true, true, null, null, null);
return(dtw.GetCost());
}
public override double GetDistance(AudioFeature f, AudioFeature.DistanceType t)
{
throw new NotImplementedException();
}
private static void FindSimilar(string path, Db db, Analyzer.AnalysisMethod analysisMethod, int numToTake=25, double percentage=0.2, AudioFeature.DistanceType distanceType = AudioFeature.DistanceType.KullbackLeiblerDivergence) {
var similarTracks = SimilarTracks(path, db, analysisMethod, numToTake, percentage, distanceType);
foreach (var entry in similarTracks)
{
Console.WriteLine("{0}, {1}", entry.Key, entry.Value);
}
}
public static void Main(string[] args) {
Analyzer.AnalysisMethod analysisMethod = Analyzer.AnalysisMethod.SCMS;
//Analyzer.AnalysisMethod analysisMethod = Analyzer.AnalysisMethod.MandelEllis;
string scanPath = "";
double skipDurationAboveSeconds = -1; // less than zero disables this
string queryPath = "";
int queryId = -1;
int numToTake = 20;
double percentage = 0.4; // percentage below and above when querying
bool resetdb = false;
bool silent = false;
AudioFeature.DistanceType distanceType = AudioFeature.DistanceType.KullbackLeiblerDivergence;
// Command line parsing
Arguments CommandLine = new Arguments(args);
if(CommandLine["match"] != null) {
queryPath = CommandLine["match"];
}
if(CommandLine["matchid"] != null) {
string matchId = CommandLine["matchid"];
queryId = int.Parse(matchId);
}
if(CommandLine["scandir"] != null) {
scanPath = CommandLine["scandir"];
}
if(CommandLine["skipduration"] != null) {
double.TryParse(CommandLine["skipduration"], NumberStyles.Number,CultureInfo.InvariantCulture, out skipDurationAboveSeconds);
}
if(CommandLine["num"] != null) {
string num = CommandLine["num"];
numToTake = int.Parse(num);
}
if(CommandLine["percentage"] != null) {
double.TryParse(CommandLine["percentage"], NumberStyles.Number,CultureInfo.InvariantCulture, out percentage);
}
if(CommandLine["type"] != null) {
string type = CommandLine["type"];
if (type.Equals("kl", StringComparison.InvariantCultureIgnoreCase)) {
distanceType = AudioFeature.DistanceType.KullbackLeiblerDivergence;
} else if (type.StartsWith("dtw", StringComparison.InvariantCultureIgnoreCase)) {
if (type.Equals("dtwe", StringComparison.InvariantCultureIgnoreCase)) {
distanceType = AudioFeature.DistanceType.Dtw_Euclidean;
} else if (type.Equals("dtwe2", StringComparison.InvariantCultureIgnoreCase)) {
distanceType = AudioFeature.DistanceType.Dtw_SquaredEuclidean;
} else if (type.Equals("dtwman", StringComparison.InvariantCultureIgnoreCase)) {
distanceType = AudioFeature.DistanceType.Dtw_Manhattan;
} else if (type.Equals("dtwmax", StringComparison.InvariantCultureIgnoreCase)) {
distanceType = AudioFeature.DistanceType.Dtw_Maximum;
} else if (type.Equals("ucrdtw", StringComparison.InvariantCultureIgnoreCase)) {
distanceType = AudioFeature.DistanceType.UCR_Dtw;
} else {
distanceType = AudioFeature.DistanceType.Dtw_Euclidean;
}
}
}
if(CommandLine["dtw"] != null || CommandLine["dtwe"] != null) {
distanceType = AudioFeature.DistanceType.Dtw_Euclidean;
}
if(CommandLine["dtwe2"] != null) {
distanceType = AudioFeature.DistanceType.Dtw_SquaredEuclidean;
}
if(CommandLine["dtwman"] != null) {
distanceType = AudioFeature.DistanceType.Dtw_Manhattan;
}
if(CommandLine["dtwmax"] != null) {
distanceType = AudioFeature.DistanceType.Dtw_Maximum;
}
if(CommandLine["kl"] != null) {
distanceType = AudioFeature.DistanceType.KullbackLeiblerDivergence;
}
if(CommandLine["ucrdtw"] != null) {
distanceType = AudioFeature.DistanceType.UCR_Dtw;
}
if(CommandLine["resetdb"] != null) {
resetdb = true;
}
if(CommandLine["silent"] != null) {
silent = true;
}
if(CommandLine["permutations"] != null) {
Console.WriteLine("Generating hash permutations for used by the Soundfingerprinting methods.");
Console.WriteLine("Saving to file: {0}", "Soundfingerprinting\\perms-new.csv");
Console.WriteLine();
PermutationGeneratorService permutationGeneratorService = new PermutationGeneratorService();
Analyzer.GenerateAndSavePermutations(permutationGeneratorService, "Soundfingerprinting\\perms-new.csv");
return;
}
if(CommandLine["?"] != null) {
PrintUsage();
return;
}
if(CommandLine["help"] != null) {
PrintUsage();
return;
}
if(CommandLine["gui"] != null) {
StartGUI();
return;
}
if (queryPath == "" && queryId == -1 && scanPath == "") {
PrintUsage();
return;
}
// Get database
Db mandelEllisScmsDatabase = new Db(); // For MandelEllis and SCMS
// Instansiate soundfingerprinting Repository
FingerprintService fingerprintService = Analyzer.GetSoundfingerprintingService();
DatabaseService databaseService = DatabaseService.Instance; // For AudioFingerprinting
IPermutations permutations = new LocalPermutations("Soundfingerprinting\\perms.csv", ",");
//IPermutations permutations = new LocalPermutations("Soundfingerprinting\\perms-new.csv", ",");
Repository repository = new Repository(permutations, databaseService, fingerprintService);
if (scanPath != "") {
if (IOUtils.IsDirectory(scanPath)) {
if (resetdb) {
// For MandelEllis and Scms
mandelEllisScmsDatabase.RemoveTable();
mandelEllisScmsDatabase.AddTable();
// For AudioFingerprinting
databaseService.RemoveFingerprintTable();
databaseService.AddFingerprintTable();
databaseService.RemoveHashBinTable();
databaseService.AddHashBinTable();
databaseService.RemoveTrackTable();
databaseService.AddTrackTable();
}
Console.WriteLine("FindSimilar. Version {0}.", VERSION);
ScanDirectory(scanPath, mandelEllisScmsDatabase, repository, skipDurationAboveSeconds, silent);
} else {
Console.Out.WriteLine("No directory found {0}!", scanPath);
}
}
if (queryPath != "") {
FileInfo fi = new FileInfo(queryPath);
if (fi.Exists) {
FindSimilar(queryPath, mandelEllisScmsDatabase, analysisMethod, numToTake, percentage, distanceType);
} else {
Console.Out.WriteLine("No file found {0}!", queryPath);
}
}
if (queryId != -1) {
FindSimilar(new int[] { queryId }, mandelEllisScmsDatabase, analysisMethod, numToTake, percentage, distanceType);
}
System.Console.ReadLine();
}
/// <summary>
/// Find Similar Tracks to one or many audio files using their unique database id(s)
/// </summary>
/// <param name="id">an array of unique database ids for the audio files to search for similar matches</param>
/// <param name="exclude">an array of unique database ids to ignore (normally the same as the id array)</param>
/// <param name="db">database</param>
/// <param name="analysisMethod">analysis method (SCMS or MandelEllis)</param>
/// <param name="numToTake">max number of entries to return</param>
/// <param name="percentage">percentage below and above the duration in ms when querying (used if between 0.1 - 0.9)</param>
/// <param name="distanceType">distance method to use (KullbackLeiblerDivergence is default)</param>
/// <returns>a list of query results</returns>
public static List<FindSimilar.QueryResult> SimilarTracksList(int[] id, int[] exclude, Db db, Analyzer.AnalysisMethod analysisMethod, int numToTake=25, double percentage=0.2, AudioFeature.DistanceType distanceType = AudioFeature.DistanceType.KullbackLeiblerDivergence) {
AudioFeature[] seedAudioFeatures = null;
AudioFeature[] audioFeatures = null;
switch (analysisMethod) {
case Analyzer.AnalysisMethod.MandelEllis:
seedAudioFeatures = new MandelEllis[id.Length];
audioFeatures = new MandelEllis[100];
break;
case Analyzer.AnalysisMethod.SCMS:
seedAudioFeatures = new Scms[id.Length];
audioFeatures = new Scms[100];
break;
}
for (int i = 0; i < seedAudioFeatures.Length; i++) {
seedAudioFeatures[i] = db.GetTrack(id[i], analysisMethod);
}
// Get all tracks from the DB except the seedSongs
IDataReader r = db.GetTracks(exclude, seedAudioFeatures[0].Duration, percentage);
// store results in a query results list
List<FindSimilar.QueryResult> queryResultList = new List<FindSimilar.QueryResult>();
int[] mapping = new int[100];
int read = 1;
double d;
double dcur;
float count;
while (read > 0) {
read = db.GetNextTracks(ref r, ref audioFeatures, ref mapping, 100, analysisMethod);
for (int i = 0; i < read; i++) {
d = 0;
count = 0;
for (int j = 0; j < seedAudioFeatures.Length; j++) {
dcur = seedAudioFeatures[j].GetDistance(audioFeatures[i], distanceType);
// convert to positive values
dcur = Math.Abs(dcur);
d += dcur;
count++;
}
if (d > 0) {
QueryResult queryResult = new QueryResult();
queryResult.Id = mapping[i];
queryResult.Path = audioFeatures[i].Name;
queryResult.Duration = audioFeatures[i].Duration;
queryResult.Similarity = d/count;
queryResultList.Add(queryResult);
}
}
}
var sortedList = (from row in queryResultList
orderby row.Similarity ascending
select new QueryResult {
Id = row.Id,
Path = row.Path,
Duration = row.Duration,
Similarity = row.Similarity
}).Take(numToTake).ToList();
return sortedList;
}
/// <summary>
/// Find Similar Tracks to one or many audio files using their unique database id(s)
/// </summary>
/// <param name="id">an array of unique database ids for the audio files to search for similar matches</param>
/// <param name="exclude">an array of unique database ids to ignore (normally the same as the id array)</param>
/// <param name="db">database</param>
/// <param name="analysisMethod">analysis method (SCMS or MandelEllis)</param>
/// <param name="numToTake">max number of entries to return</param>
/// <param name="percentage">percentage below and above the duration in ms when querying (used if between 0.1 - 0.9)</param>
/// <param name="distanceType">distance method to use (KullbackLeiblerDivergence is default)</param>
/// <returns>a dictinary list of key value pairs (filepath and distance)</returns>
public static Dictionary<KeyValuePair<int, string>, double> SimilarTracks(int[] id, int[] exclude, Db db, Analyzer.AnalysisMethod analysisMethod, int numToTake=25, double percentage=0.2, AudioFeature.DistanceType distanceType = AudioFeature.DistanceType.KullbackLeiblerDivergence)
{
DbgTimer t = new DbgTimer();
t.Start();
AudioFeature[] seedAudioFeatures = null;
AudioFeature[] audioFeatures = null;
switch (analysisMethod) {
case Analyzer.AnalysisMethod.MandelEllis:
seedAudioFeatures = new MandelEllis[id.Length];
audioFeatures = new MandelEllis[100];
break;
case Analyzer.AnalysisMethod.SCMS:
seedAudioFeatures = new Scms[id.Length];
audioFeatures = new Scms[100];
break;
}
for (int i = 0; i < seedAudioFeatures.Length; i++) {
seedAudioFeatures[i] = db.GetTrack(id[i], analysisMethod);
}
// Get all tracks from the DB except the seedSongs
IDataReader r = db.GetTracks(exclude, seedAudioFeatures[0].Duration, percentage);
// store results in a dictionary
var NameDictionary = new Dictionary<KeyValuePair<int, string>, double>();
int[] mapping = new int[100];
int read = 1;
double d;
double dcur;
float count;
while (read > 0) {
read = db.GetNextTracks(ref r, ref audioFeatures, ref mapping, 100, analysisMethod);
for (int i = 0; i < read; i++) {
d = 0;
count = 0;
for (int j = 0; j < seedAudioFeatures.Length; j++) {
dcur = seedAudioFeatures[j].GetDistance(audioFeatures[i], distanceType);
// convert to positive values
dcur = Math.Abs(dcur);
d += dcur;
count++;
}
if (d > 0) {
NameDictionary.Add(new KeyValuePair<int,string>(mapping[i], audioFeatures[i].Name), d/count);
//NameDictionary.Add(new KeyValuePair<int,string>(mapping[i], String.Format("{0} ({1} ms)", audioFeatures[i].Name, audioFeatures[i].Duration)), d/count);
}
}
}
// sort by non unique values
var sortedDict = (from entry in NameDictionary orderby entry.Value ascending select entry)
.Take(numToTake)
.ToDictionary(pair => pair.Key, pair => pair.Value);
Console.Out.WriteLine(String.Format("Found Similar to ({0}) in {1} ms", String.Join(",", seedAudioFeatures.Select(p=>p.Name)), t.Stop().TotalMilliseconds));
return sortedDict;
}
/// <summary>
/// Find Similar Tracks to an audio file using its file path
/// </summary>
/// <param name="searchForPath">audio file path</param>
/// <param name="db">database</param>
/// <param name="analysisMethod">analysis method (SCMS or MandelEllis)</param>
/// <param name="numToTake">max number of entries to return</param>
/// <param name="percentage">percentage below and above the duration in ms when querying (used if between 0.1 - 0.9)</param>
/// <param name="distanceType">distance method to use (KullbackLeiblerDivergence is default)</param>
/// <returns>a list of query results</returns>
public static List<FindSimilar.QueryResult> SimilarTracksList(string searchForPath, Db db, Analyzer.AnalysisMethod analysisMethod, int numToTake=25, double percentage=0.2, AudioFeature.DistanceType distanceType = AudioFeature.DistanceType.KullbackLeiblerDivergence) {
FileInfo fi = new FileInfo(searchForPath);
AudioFeature seedAudioFeature = null;
AudioFeature[] audioFeatures = null;
switch (analysisMethod) {
case Analyzer.AnalysisMethod.MandelEllis:
seedAudioFeature = Analyzer.AnalyzeMandelEllis(fi);
audioFeatures = new MandelEllis[100];
break;
case Analyzer.AnalysisMethod.SCMS:
seedAudioFeature = Analyzer.AnalyzeScms(fi);
audioFeatures = new Scms[100];
break;
}
// Get all tracks from the DB except the seedSongs
IDataReader r = db.GetTracks(null, seedAudioFeature.Duration, percentage);
// store results in a query results list
List<FindSimilar.QueryResult> queryResultList = new List<FindSimilar.QueryResult>();
int[] mapping = new int[100];
int read = 1;
double dcur;
while (read > 0) {
read = db.GetNextTracks(ref r, ref audioFeatures, ref mapping, 100, analysisMethod);
for (int i = 0; i < read; i++) {
dcur = seedAudioFeature.GetDistance(audioFeatures[i], distanceType);
// convert to positive values
dcur = Math.Abs(dcur);
QueryResult queryResult = new QueryResult();
queryResult.Id = mapping[i];
queryResult.Path = audioFeatures[i].Name;
queryResult.Duration = audioFeatures[i].Duration;
queryResult.Similarity = dcur;
queryResultList.Add(queryResult);
}
}
var sortedList = (from row in queryResultList
orderby row.Similarity ascending
select new QueryResult {
Id = row.Id,
Path = row.Path,
Duration = row.Duration,
Similarity = row.Similarity
}).Take(numToTake).ToList();
return sortedList;
}
/// <summary>
/// Find Similar Tracks to an audio file using its file path
/// </summary>
/// <param name="searchForPath">audio file path</param>
/// <param name="db">database</param>
/// <param name="analysisMethod">analysis method (SCMS or MandelEllis)</param>
/// <param name="numToTake">max number of entries to return</param>
/// <param name="percentage">percentage below and above the duration in ms when querying (used if between 0.1 - 0.9)</param>
/// <param name="distanceType">distance method to use (KullbackLeiblerDivergence is default)</param>
/// <returns>a dictinary list of key value pairs (filepath and distance)</returns>
public static Dictionary<KeyValuePair<int, string>, double> SimilarTracks(string searchForPath, Db db, Analyzer.AnalysisMethod analysisMethod, int numToTake=25, double percentage=0.2, AudioFeature.DistanceType distanceType = AudioFeature.DistanceType.KullbackLeiblerDivergence)
{
DbgTimer t = new DbgTimer();
t.Start();
FileInfo fi = new FileInfo(searchForPath);
AudioFeature seedAudioFeature = null;
AudioFeature[] audioFeatures = null;
switch (analysisMethod) {
case Analyzer.AnalysisMethod.MandelEllis:
seedAudioFeature = Analyzer.AnalyzeMandelEllis(fi);
audioFeatures = new MandelEllis[100];
break;
case Analyzer.AnalysisMethod.SCMS:
seedAudioFeature = Analyzer.AnalyzeScms(fi);
audioFeatures = new Scms[100];
break;
}
// Get all tracks from the DB except the seedSongs
IDataReader r = db.GetTracks(null, seedAudioFeature.Duration, percentage);
// store results in a dictionary
var NameDictionary = new Dictionary<KeyValuePair<int, string>, double>();
int[] mapping = new int[100];
int read = 1;
double dcur;
while (read > 0) {
read = db.GetNextTracks(ref r, ref audioFeatures, ref mapping, 100, analysisMethod);
for (int i = 0; i < read; i++) {
dcur = seedAudioFeature.GetDistance(audioFeatures[i], distanceType);
// convert to positive values
dcur = Math.Abs(dcur);
NameDictionary.Add(new KeyValuePair<int,string>(mapping[i], audioFeatures[i].Name), dcur);
}
}
// sort by non unique values
var sortedDict = (from entry in NameDictionary orderby entry.Value ascending select entry)
.Take(numToTake)
.ToDictionary(pair => pair.Key, pair => pair.Value);
Console.Out.WriteLine(String.Format("Found Similar to ({0}) in {1} ms", seedAudioFeature.Name, t.Stop().TotalMilliseconds));
return sortedDict;
}
