Harden speaker identity samples

2026-05-28 12:02:44 +02:00
parent c84f8a984a
commit a72cda0c03
23 changed files with 1251 additions and 123 deletions
@@ -0,0 +1,79 @@
+using MeetingAssistant.Transcription;
+
+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(
+        IReadOnlyList<TranscriptionSegment> segments,
+        string speaker,
+        TimeSpan maximumSegmentGap,
+        TimeSpan minimumDuration)
+    {
+        var best = new List<TranscriptionSegment>();
+        var current = new List<TranscriptionSegment>();
+
+        foreach (var segment in segments.OrderBy(segment => segment.Start))
+        {
+            if (current.Count == 0)
+            {
+                if (IsSpeaker(segment, speaker))
+                {
+                    current.Add(segment);
+                    best = LongerSpan(current, best);
+                }
+
+                continue;
+            }
+
+            if (!CanExtend(speaker, current[^1].End, segment, maximumSegmentGap))
+            {
+                current.Clear();
+                if (!IsSpeaker(segment, speaker))
+                {
+                    continue;
+                }
+            }
+
+            current.Add(segment);
+            best = LongerSpan(current, best);
+        }
+
+        return SpanDuration(best) >= minimumDuration
+            ? best
+            : [];
+    }
+
+    public static TimeSpan SpanDuration(IReadOnlyList<TranscriptionSegment> segments)
+    {
+        return segments.Count == 0
+            ? TimeSpan.Zero
+            : segments[^1].End - segments[0].Start;
+    }
+
+    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;
+    }
+}