feat: add local Resemblyzer speaker recognition

MeetingAssistant/Speakers/SpeakerSampleCollectionPolicy.cs

@@ -0,0 +1,154 @@
+using Microsoft.Extensions.Options;
+
+namespace MeetingAssistant.Speakers;
+
+public sealed record SpeakerSampleCollectionPolicy(
+    int MinimumRetainedSamples,
+    bool RequireNonOverlappingSamples)
+{
+    public static SpeakerSampleCollectionPolicy ExistingBackend { get; } = new(1, false);
+
+    public static SpeakerSampleCollectionPolicy IndependentVectors(int maximumVectors)
+    {
+        return new SpeakerSampleCollectionPolicy(Math.Max(1, maximumVectors), true);
+    }
+
+    public int ResolveRetainedSampleLimit(int configuredLimit)
+    {
+        return Math.Max(Math.Max(1, configuredLimit), MinimumRetainedSamples);
+    }
+}
+
+internal static class SpeakerSampleDurationConfiguration
+{
+    public static void ValidateOrThrow(
+        SpeakerIdentificationOptions options,
+        string context)
+    {
+        ValidateOrThrow(
+            options.MinimumSampleSpeechDuration,
+            options.MaximumSampleDuration,
+            context);
+    }
+
+    public static void ValidateOrThrow(
+        TimeSpan minimumDuration,
+        TimeSpan maximumDuration,
+        string context)
+    {
+        var error = GetError(minimumDuration, maximumDuration);
+        if (error is not null)
+        {
+            throw new InvalidOperationException($"{context}: {error}");
+        }
+    }
+
+    public static string? GetError(
+        TimeSpan minimumDuration,
+        TimeSpan maximumDuration)
+    {
+        if (minimumDuration < TimeSpan.Zero)
+        {
+            return "SpeakerIdentification:MinimumSampleSpeechDuration must not be negative.";
+        }
+
+        if (maximumDuration <= TimeSpan.Zero)
+        {
+            return "SpeakerIdentification:MaximumSampleDuration must be greater than zero.";
+        }
+
+        return minimumDuration > maximumDuration
+            ? "SpeakerIdentification:MinimumSampleSpeechDuration must not exceed SpeakerIdentification:MaximumSampleDuration."
+            : null;
+    }
+}
+
+internal static class ResemblyzerSpeakerRecognitionConfiguration
+{
+    public static void ValidateOrThrow(
+        ResemblyzerSpeakerRecognitionOptions options,
+        string context)
+    {
+        var error = GetError(options);
+        if (error is not null)
+        {
+            throw new InvalidOperationException($"{context}: {error}");
+        }
+    }
+
+    public static string? GetError(ResemblyzerSpeakerRecognitionOptions options)
+    {
+        if (options.RequiredVectorsPerSpeaker < 1)
+        {
+            return "SpeakerIdentification:Resemblyzer:RequiredVectorsPerSpeaker must be at least one.";
+        }
+
+        if (options.MaxVectorsPerIdentity < options.RequiredVectorsPerSpeaker)
+        {
+            return "SpeakerIdentification:Resemblyzer:MaxVectorsPerIdentity must not be less than RequiredVectorsPerSpeaker.";
+        }
+
+        if (options.OutlierPruningMinimumVectors < options.RequiredVectorsPerSpeaker)
+        {
+            return "SpeakerIdentification:Resemblyzer:OutlierPruningMinimumVectors must not be less than RequiredVectorsPerSpeaker.";
+        }
+
+        if (options.OutlierPruningMinimumVectors > options.MaxVectorsPerIdentity)
+        {
+            return "SpeakerIdentification:Resemblyzer:OutlierPruningMinimumVectors must not exceed MaxVectorsPerIdentity.";
+        }
+
+        if (options.OutlierPruningMinimumNeighbors < 1 ||
+            options.OutlierPruningMinimumNeighbors > options.OutlierPruningMinimumVectors)
+        {
+            return "SpeakerIdentification:Resemblyzer:OutlierPruningMinimumNeighbors must be between one and OutlierPruningMinimumVectors.";
+        }
+
+        if (!IsCosine(options.OutlierPruningNeighborSimilarity))
+        {
+            return "SpeakerIdentification:Resemblyzer:OutlierPruningNeighborSimilarity must be finite and between -1 and 1.";
+        }
+
+        if (!double.IsFinite(options.OutlierPruningMinimumClusterRatio) ||
+            options.OutlierPruningMinimumClusterRatio is <= 0 or > 1)
+        {
+            return "SpeakerIdentification:Resemblyzer:OutlierPruningMinimumClusterRatio must be finite, greater than zero, and at most one.";
+        }
+
+        if (!IsCosine(options.MinimumClusterCohesion))
+        {
+            return "SpeakerIdentification:Resemblyzer:MinimumClusterCohesion must be finite and between -1 and 1.";
+        }
+
+        if (!IsCosine(options.MinimumIdentitySimilarity))
+        {
+            return "SpeakerIdentification:Resemblyzer:MinimumIdentitySimilarity must be finite and between -1 and 1.";
+        }
+
+        return !double.IsFinite(options.MinimumSimilarityMargin) ||
+            options.MinimumSimilarityMargin is < 0 or > 2
+            ? "SpeakerIdentification:Resemblyzer:MinimumSimilarityMargin must be finite and between 0 and 2."
+            : null;
+    }
+
+    private static bool IsCosine(double value)
+    {
+        return double.IsFinite(value) && value is >= -1 and <= 1;
+    }
+}
+
+internal sealed class MeetingAssistantSpeakerSampleOptionsValidator
+    : IValidateOptions<MeetingAssistantOptions>
+{
+    public ValidateOptionsResult Validate(string? name, MeetingAssistantOptions options)
+    {
+        var error = SpeakerSampleDurationConfiguration.GetError(
+            options.SpeakerIdentification.MinimumSampleSpeechDuration,
+            options.SpeakerIdentification.MaximumSampleDuration) ??
+            ResemblyzerSpeakerRecognitionConfiguration.GetError(
+                options.SpeakerIdentification.Resemblyzer);
+        return error is null
+            ? ValidateOptionsResult.Success
+            : ValidateOptionsResult.Fail(error);
+    }
+}