Harden speaker identity samples

MeetingAssistant/Recording/MeetingRecordingCoordinator.cs

@@ -1334,7 +1334,11 @@ public sealed class MeetingRecordingCoordinator
             Options = options;
             LaunchProfileName = launchProfileName;
             pipelines.Add(pipeline);
-            speakerSampleCollector = new SpeakerAudioSampleCollector(liveSampleBufferDuration, maxSpeakerSamples);
+            speakerSampleCollector = new SpeakerAudioSampleCollector(
+                liveSampleBufferDuration,
+                maxSpeakerSamples,
+                options.SpeakerIdentification.MinimumSampleSpeechDuration,
+                options.SpeakerIdentification.MaximumSampleSegmentGap);
         }
 
         public CancellationTokenSource CaptureCancellationSource { get; }

MeetingAssistant/Recording/SpeakerAudioSampleCollector.cs

@@ -9,11 +9,33 @@ internal sealed class SpeakerAudioSampleCollector
     private readonly RollingAudioBuffer audioBuffer;
     private readonly Dictionary<string, List<SpeakerAudioSample>> samplesBySpeaker = new(StringComparer.OrdinalIgnoreCase);
     private readonly int maxSamplesPerSpeaker;
+    private readonly TimeSpan minimumUninterruptedSpeechDuration;
+    private readonly TimeSpan maximumSegmentGap;
+    private PendingSpeakerSpan? pendingSpan;
 
     public SpeakerAudioSampleCollector(TimeSpan bufferDuration, int maxSamplesPerSpeaker)
+        : this(
+            bufferDuration,
+            maxSamplesPerSpeaker,
+            TimeSpan.FromSeconds(30),
+            TimeSpan.FromSeconds(1))
+    {
+    }
+
+    public SpeakerAudioSampleCollector(
+        TimeSpan bufferDuration,
+        int maxSamplesPerSpeaker,
+        TimeSpan minimumUninterruptedSpeechDuration,
+        TimeSpan maximumSegmentGap)
     {
         audioBuffer = new RollingAudioBuffer(bufferDuration);
         this.maxSamplesPerSpeaker = Math.Max(1, maxSamplesPerSpeaker);
+        this.minimumUninterruptedSpeechDuration = minimumUninterruptedSpeechDuration > TimeSpan.Zero
+            ? minimumUninterruptedSpeechDuration
+            : TimeSpan.Zero;
+        this.maximumSegmentGap = maximumSegmentGap >= TimeSpan.Zero
+            ? maximumSegmentGap
+            : TimeSpan.Zero;
     }
 
     public void AppendAudio(AudioChunk chunk)
@@ -26,6 +48,7 @@ internal sealed class SpeakerAudioSampleCollector
         lock (gate)
         {
             samplesBySpeaker.Clear();
+            pendingSpan = null;
             audioBuffer.Reset();
         }
     }
@@ -37,25 +60,31 @@ internal sealed class SpeakerAudioSampleCollector
             return;
         }
 
-        var score = Score(segment);
+        TranscriptionSegment sampleSegment;
+        lock (gate)
+        {
+            sampleSegment = ExtendPendingSpan(segment);
+        }
+
+        var score = Score(sampleSegment, minimumUninterruptedSpeechDuration);
         if (score <= 0)
         {
             return;
         }
 
-        var wavBytes = audioBuffer.TryExtractWav(segment.Start, segment.End);
+        var wavBytes = audioBuffer.TryExtractWav(sampleSegment.Start, sampleSegment.End);
         if (wavBytes.Length == 0)
         {
             return;
         }
 
-        var sample = new SpeakerAudioSample(segment.Speaker, segment, wavBytes, score);
+        var sample = new SpeakerAudioSample(sampleSegment.Speaker, sampleSegment, wavBytes, score);
         lock (gate)
         {
-            if (!samplesBySpeaker.TryGetValue(segment.Speaker, out var samples))
+            if (!samplesBySpeaker.TryGetValue(sampleSegment.Speaker, out var samples))
             {
                 samples = [];
-                samplesBySpeaker[segment.Speaker] = samples;
+                samplesBySpeaker[sampleSegment.Speaker] = samples;
             }
 
             samples.Add(sample);
@@ -86,10 +115,29 @@ internal sealed class SpeakerAudioSampleCollector
             !string.Equals(speaker, "Unknown", StringComparison.OrdinalIgnoreCase);
     }
 
-    private static double Score(TranscriptionSegment segment)
+    private TranscriptionSegment ExtendPendingSpan(TranscriptionSegment segment)
+    {
+        if (pendingSpan is null ||
+            !SpeakerSampleSpanSelector.CanExtend(pendingSpan.Speaker, pendingSpan.End, segment, maximumSegmentGap))
+        {
+            pendingSpan = new PendingSpeakerSpan(
+                segment.Speaker,
+                segment.Start,
+                segment.End,
+                [segment.Text]);
+            return pendingSpan.ToSegment();
+        }
+
+        pendingSpan = pendingSpan.Extend(segment);
+        return pendingSpan.ToSegment();
+    }
+
+    private static double Score(
+        TranscriptionSegment segment,
+        TimeSpan minimumUninterruptedSpeechDuration)
     {
         var durationSeconds = (segment.End - segment.Start).TotalSeconds;
-        if (durationSeconds < 2 || durationSeconds > 30)
+        if (durationSeconds < minimumUninterruptedSpeechDuration.TotalSeconds)
         {
             return 0;
         }
@@ -97,13 +145,13 @@ internal sealed class SpeakerAudioSampleCollector
         var words = segment.Text
             .Split(' ', StringSplitOptions.RemoveEmptyEntries | StringSplitOptions.TrimEntries)
             .Length;
-        if (words < 3 || words > 80)
+        if (words < 3)
         {
             return 0;
         }
 
-        var durationScore = 1 - Math.Min(Math.Abs(durationSeconds - 8) / 8, 1);
-        var wordScore = 1 - Math.Min(Math.Abs(words - 18) / 18.0, 1);
+        var durationScore = Math.Min(durationSeconds / Math.Max(1, minimumUninterruptedSpeechDuration.TotalSeconds), 2);
+        var wordScore = Math.Min(words / 60.0, 1);
         var sentenceBonus = segment.Text.TrimEnd().EndsWith('.') ||
             segment.Text.TrimEnd().EndsWith('?') ||
             segment.Text.TrimEnd().EndsWith('!')
@@ -111,4 +159,29 @@ internal sealed class SpeakerAudioSampleCollector
                 : 0;
         return durationScore * 70 + wordScore * 30 + sentenceBonus;
     }
+
+    private sealed record PendingSpeakerSpan(
+        string Speaker,
+        TimeSpan Start,
+        TimeSpan End,
+        IReadOnlyList<string> TextParts)
+    {
+        public PendingSpeakerSpan Extend(TranscriptionSegment segment)
+        {
+            return this with
+            {
+                End = segment.End > End ? segment.End : End,
+                TextParts = TextParts.Append(segment.Text).ToList()
+            };
+        }
+
+        public TranscriptionSegment ToSegment()
+        {
+            return new TranscriptionSegment(
+                Start,
+                End,
+                Speaker,
+                string.Join(' ', TextParts.Where(part => !string.IsNullOrWhiteSpace(part))));
+        }
+    }
 }