feat: add local Resemblyzer speaker recognition

2026-09-11 13:49:27 +02:00
parent 43fc8aaec0
commit f86af983e8
48 changed files with 5250 additions and 273 deletions
@@ -0,0 +1,122 @@
+using MeetingAssistant;
+using MeetingAssistant.Speakers;
+using Microsoft.Extensions.Logging.Abstractions;
+
+namespace MeetingAssistant.Tests;
+
+public sealed class ResemblyzerVoiceClusterMatcherTests
+{
+    [Fact]
+    public void CoherentSimilarClusterSelectsUnambiguousIdentity()
+    {
+        var matcher = CreateMatcher();
+        var query = Enumerable.Range(0, 5)
+            .Select(index => UnitVector(0, secondaryDimension: index + 2, secondaryValue: 0.05f))
+            .ToList();
+        var candidates = new[]
+        {
+            new ResemblyzerVoiceVectorCandidate(42, [UnitVector(0), UnitVector(0, 10, 0.02f)]),
+            new ResemblyzerVoiceVectorCandidate(77, [UnitVector(1), UnitVector(1, 11, 0.02f)])
+        };
+
+        var result = matcher.Match(query, candidates);
+
+        Assert.True(result.Accepted);
+        Assert.Equal(42, result.IdentityId);
+        Assert.True(result.Cohesion >= 0.99);
+        Assert.True(result.BestSimilarity >= 0.99);
+        Assert.True(result.RunnerUpSimilarity < 0.1);
+    }
+
+    [Fact]
+    public void FourVectorsDoNotTriggerAutomaticMatching()
+    {
+        var result = CreateMatcher().Match(
+            Enumerable.Repeat(UnitVector(0), 4).ToList(),
+            [new ResemblyzerVoiceVectorCandidate(42, [UnitVector(0)])]);
+
+        Assert.False(result.Accepted);
+        Assert.Contains("4/5", result.Reason);
+    }
+
+    [Fact]
+    public void IncoherentClusterIsRejectedBeforeIdentityScoring()
+    {
+        var result = CreateMatcher().Match(
+            Enumerable.Range(0, 5).Select(index => UnitVector(index)).ToList(),
+            [new ResemblyzerVoiceVectorCandidate(42, [UnitVector(0)])]);
+
+        Assert.False(result.Accepted);
+        Assert.Contains("cohesion", result.Reason);
+        Assert.Null(result.BestSimilarity);
+    }
+
+    [Fact]
+    public void SimilarityBelowThresholdIsRejected()
+    {
+        var result = CreateMatcher().Match(
+            Enumerable.Repeat(UnitVector(0), 5).ToList(),
+            [new ResemblyzerVoiceVectorCandidate(42, [UnitVector(1)])]);
+
+        Assert.False(result.Accepted);
+        Assert.Contains("best similarity", result.Reason);
+        Assert.Equal(0, result.BestSimilarity);
+    }
+
+    [Fact]
+    public void SimilarCandidatesWithinMarginAreRejected()
+    {
+        var result = CreateMatcher().Match(
+            Enumerable.Repeat(UnitVector(0), 5).ToList(),
+            [
+                new ResemblyzerVoiceVectorCandidate(42, [UnitVector(0)]),
+                new ResemblyzerVoiceVectorCandidate(77, [UnitVector(0, 1, 0.01f)])
+            ]);
+
+        Assert.False(result.Accepted);
+        Assert.Contains("margin", result.Reason);
+        Assert.NotNull(result.RunnerUpSimilarity);
+    }
+
+    [Fact]
+    public void InvalidStoredCandidateDoesNotAbortScoringOtherIdentities()
+    {
+        var result = CreateMatcher().Match(
+            Enumerable.Repeat(UnitVector(0), 5).ToList(),
+            [
+                new ResemblyzerVoiceVectorCandidate(13, [new float[256]]),
+                new ResemblyzerVoiceVectorCandidate(42, [UnitVector(0)])
+            ]);
+
+        Assert.True(result.Accepted);
+        Assert.Equal(42, result.IdentityId);
+    }
+
+    private static ResemblyzerVoiceClusterMatcher CreateMatcher()
+    {
+        return new ResemblyzerVoiceClusterMatcher(
+            new ResemblyzerSpeakerRecognitionOptions
+            {
+                RequiredVectorsPerSpeaker = 5,
+                MinimumClusterCohesion = 0.75,
+                MinimumIdentitySimilarity = 0.75,
+                MinimumSimilarityMargin = 0.05
+            },
+            NullLogger<ResemblyzerVoiceClusterMatcher>.Instance);
+    }
+
+    private static float[] UnitVector(
+        int primaryDimension,
+        int? secondaryDimension = null,
+        float secondaryValue = 0)
+    {
+        var vector = new float[256];
+        vector[primaryDimension] = 1;
+        if (secondaryDimension is { } dimension)
+        {
+            vector[dimension] = secondaryValue;
+        }
+
+        return vector;
+    }
+}