Changes to standard spectrogram config file

For drawing standard spectrograms. Also some minor changes to Audio2Sonogram.cs class.
QutEcoacoustics · Dec 6, 2019 · b93a667 · b93a667
1 parent b160627
commit b93a667
Show file tree

Hide file tree

Showing 2 changed files with 29 additions and 25 deletions.
diff --git a/src/AnalysisConfigFiles/Towsey.Sonogram.yml b/src/AnalysisConfigFiles/Towsey.Sonogram.yml
@@ -1,37 +1,47 @@
 ---
 AnalysisName: Towsey.SpectrogramGenerator
-#SegmentDuration: units=seconds,   SegmentOverlap=seconds
+
+# Generate multiple standard-scale spectrogram images and oscillations info
+
+# Usage: AnalysisPrograms.exe Audio2Sonogram [arguments] [options]
+#Arguments:
+#  Source: The source audio file to operate on
+#  Config  The path to this config file. If not found it will attempt to use a default config file of the same name.
+#  Output  A directory to write output
+
+#Following segmentation parameters are default and should usually not be changed. Units are seconds.
 SegmentDuration: 60
 SegmentOverlap: 0
 
+#Resample rate must be 2 X the desired Nyquist.
 ResampleRate: 22050
+# WARNING: The default SR = 22050.
+# IF you want to keep the recording SR AND it is NOT 22050, THEN you must set the ResampleRate value here
+# ResampleRate: 20000
+
 #FRAME LENGTH in samples - must be power of 2
 FrameLength: 512
+# Following frame step yields 50 frames/s which can make some subsequent operations a bit easier.
+FrameStep: 441
 
-#Frame Overlap as fraction: default=0.0
-FrameOverlap: 0.25
-
-#Resample rate must be 2 X the desired Nyquist.
-# WARNING: Default SR used to be the SR of the recording. NOW DEFAULT = 22050.
-# IF you want to keep the recording SR AND it is NOT 22050, THEN you must set the ResampleRate value here
-# ResampleRate: 20000
+Waveform: true
+PowerSpectrogram: true
+DecibelSpectrogram: true
+PowerSpectrogram_NoiseReduced: true
+PowerSpectrogram_Annotated: true
+AmplitudeSpectrogram_LocalContrastNormalisation: true
 
 #NOISE REDUCTION PARAMETERS
 DoNoiseReduction: true
 NoiseReductionType: Standard
 BgNoiseThreshold: 3.0
 LcnContrastLevel: 0.4
 
-
 AddAxes: true
 AddSegmentationTrack: true
 VOCAL_GAP: 0.1
 MIN_VOCAL_DURATION: 0.1
 
-# REDUCTION FACTORS for freq and time dimensions
-#TimeReductionFactor: 1
-#FreqReductionFactor: 1
-
 MakeSoxSonogram: false
 SonogramTitle: Sonogram
 SonogramComment: "Sonogram produced using SOX"

diff --git a/src/AnalysisPrograms/Audio2Sonogram.cs b/src/AnalysisPrograms/Audio2Sonogram.cs
@@ -1,4 +1,4 @@
-// --------------------------------------------------------------------------------------------------------------------
+// --------------------------------------------------------------------------------------------------------------------
 // <copyright file="Audio2Sonogram.cs" company="QutEcoacoustics">
 // All code in this file and all associated files are the copyright and property of the QUT Ecoacoustics Research Group (formerly MQUTeR, and formerly QUT Bioacoustics Research Group).
 // </copyright>
@@ -22,24 +22,22 @@ namespace AnalysisPrograms
     using Acoustics.Shared;
     using Acoustics.Shared.ConfigFile;
     using Acoustics.Shared.Csv;
-    using Acoustics.Tools.Wav;
     using AnalysisBase;
     using AnalysisBase.ResultBases;
+    using AnalysisPrograms.Production;
+    using AnalysisPrograms.Production.Arguments;
+    using AnalysisPrograms.Production.Validation;
     using AudioAnalysisTools;
     using AudioAnalysisTools.DSP;
     using AudioAnalysisTools.StandardSpectrograms;
     using AudioAnalysisTools.WavTools;
     using log4net;
     using MathNet.Numerics;
     using McMaster.Extensions.CommandLineUtils;
-    using Production;
-    using Production.Arguments;
-    using Production.Validation;
     using TowseyLibrary;
 
     /// <summary>
-    /// 3. Produces a sonogram from an audio file - EITHER custom OR via SOX
-    /// Signed off: Michael Towsey 31st July 2012
+    /// Produces standard greyscale spectrograms of various types from a wav audio file - EITHER custom OR via SOX.
     /// </summary>
     public class Audio2Sonogram
     {
@@ -88,7 +86,7 @@ public static void Main(Arguments arguments)
 
             var offsetsProvided = arguments.StartOffset.HasValue && arguments.EndOffset.HasValue;
 
-            // set default offsets - only use defaults if not provided in argments list
+            // set default offsets - only use defaults if not provided in arguments list
             TimeSpan? startOffset = null;
             TimeSpan? endOffset = null;
             if (offsetsProvided)
@@ -143,10 +141,6 @@ private static Dictionary<string, string> GetConfigDictionary(FileInfo configFil
                 [AnalysisKeys.AddSegmentationTrack] = (configuration.GetBoolOrNull(AnalysisKeys.AddSegmentationTrack) ?? true).ToString(),
             };
 
-            // # REDUCTION FACTORS for freq and time dimensions
-            // #TimeReductionFactor: 1
-            // #FreqReductionFactor: 1
-
             bool makeSoxSonogram = configuration.GetBoolOrNull(AnalysisKeys.MakeSoxSonogram) ?? false;
             configDict[AnalysisKeys.SonogramTitle] = configuration[AnalysisKeys.SonogramTitle] ?? "Sonogram";
             configDict[AnalysisKeys.SonogramComment] = configuration[AnalysisKeys.SonogramComment] ?? "Sonogram produced using SOX";