feat: add local Resemblyzer speaker recognition

MeetingAssistant/Speakers/SpeakerSampleSpanSelector.cs

@@ -4,56 +4,84 @@ namespace MeetingAssistant.Speakers;
 
 internal static class SpeakerSampleSpanSelector
 {
-    public static bool CanExtend(
-        string currentSpeaker,
-        TimeSpan currentEnd,
-        TranscriptionSegment nextSegment,
-        TimeSpan maximumSegmentGap)
-    {
-        return string.Equals(currentSpeaker, nextSegment.Speaker, StringComparison.OrdinalIgnoreCase) &&
-            nextSegment.Start - currentEnd <= maximumSegmentGap;
-    }
-
-    public static IReadOnlyList<TranscriptionSegment> SelectBestContinuousSpan(
+    public static IReadOnlyList<TranscriptionSegment> SelectBestSameSpeakerSpan(
         IReadOnlyList<TranscriptionSegment> segments,
         string speaker,
-        TimeSpan maximumSegmentGap,
-        TimeSpan minimumDuration)
+        TimeSpan minimumDuration,
+        TimeSpan maximumSampleDuration)
     {
-        var best = new List<TranscriptionSegment>();
-        var current = new List<TranscriptionSegment>();
-
+        SpeakerSampleSpan? best = null;
+        SpeakerSampleSpan? current = null;
         foreach (var segment in segments.OrderBy(segment => segment.Start))
         {
-            if (current.Count == 0)
+            if (!IsSpeaker(segment, speaker))
             {
-                if (IsSpeaker(segment, speaker))
-                {
-                    current.Add(segment);
-                    best = LongerSpan(current, best);
-                }
-
+                current = null;
                 continue;
             }
 
-            if (!CanExtend(speaker, current[^1].End, segment, maximumSegmentGap))
+            current = ExtendOrStart(current, segment, maximumSampleDuration);
+            if (current is not null &&
+                (best is null || current.SpeechDuration > best.SpeechDuration))
             {
-                current.Clear();
-                if (!IsSpeaker(segment, speaker))
-                {
-                    continue;
-                }
+                best = current;
             }
-
-            current.Add(segment);
-            best = LongerSpan(current, best);
         }
 
-        return SpanDuration(best) >= minimumDuration
-            ? best
+        return best is not null && best.SpeechDuration >= minimumDuration
+            ? best.Segments
             : [];
     }
 
+    public static IReadOnlyList<IReadOnlyList<TranscriptionSegment>> SelectBestSameSpeakerSpans(
+        IReadOnlyList<TranscriptionSegment> segments,
+        string speaker,
+        TimeSpan minimumDuration,
+        TimeSpan maximumSampleDuration,
+        int maxSpans)
+    {
+        if (maxSpans <= 0)
+        {
+            return [];
+        }
+
+        var completed = new List<SpeakerSampleSpan>();
+        SpeakerSampleSpan? current = null;
+        TimeSpan? lastCompletedEnd = null;
+        foreach (var segment in segments.OrderBy(segment => segment.Start))
+        {
+            if (!IsSpeaker(segment, speaker))
+            {
+                current = null;
+                continue;
+            }
+
+            if (lastCompletedEnd is { } end && segment.Start < end)
+            {
+                current = null;
+                continue;
+            }
+
+            current = ExtendOrStart(current, segment, maximumSampleDuration);
+            if (current is null || current.SpeechDuration < minimumDuration)
+            {
+                continue;
+            }
+
+            completed.Add(current);
+            lastCompletedEnd = current.End;
+            current = null;
+        }
+
+        return completed
+            .OrderByDescending(span => span.SpeechDuration)
+            .ThenBy(span => span.Start)
+            .Take(maxSpans)
+            .OrderBy(span => span.Start)
+            .Select(span => span.Segments)
+            .ToList();
+    }
+
     public static TimeSpan SpanDuration(IReadOnlyList<TranscriptionSegment> segments)
     {
         return segments.Count == 0
@@ -61,19 +89,20 @@ internal static class SpeakerSampleSpanSelector
             : segments[^1].End - segments[0].Start;
     }
 
+    private static SpeakerSampleSpan? ExtendOrStart(
+        SpeakerSampleSpan? current,
+        TranscriptionSegment segment,
+        TimeSpan maximumSampleDuration)
+    {
+        return current is not null && current.TryExtend(segment, out var extended)
+            ? extended
+            : SpeakerSampleSpan.Create(segment, maximumSampleDuration);
+    }
+
     private static bool IsSpeaker(
         TranscriptionSegment segment,
         string speaker)
     {
         return string.Equals(segment.Speaker, speaker, StringComparison.OrdinalIgnoreCase);
     }
-
-    private static List<TranscriptionSegment> LongerSpan(
-        List<TranscriptionSegment> current,
-        List<TranscriptionSegment> best)
-    {
-        return SpanDuration(current) > SpanDuration(best)
-            ? current.ToList()
-            : best;
-    }
 }