Harden speaker identity samples

MeetingAssistant/Speakers/SpeakerIdentityService.cs

@@ -10,6 +10,7 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
     private readonly IDbContextFactory<SpeakerIdentityDbContext> dbContextFactory;
     private readonly ISpeakerSnippetExtractor snippetExtractor;
     private readonly ISpeakerIdentityMatcher matcher;
+    private readonly ISpeakerIdentityMatchValidator matchValidator;
     private readonly SpeakerIdentificationOptions options;
     private readonly ILogger<SpeakerIdentityService> logger;
 
@@ -18,11 +19,13 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
         ISpeakerSnippetExtractor snippetExtractor,
         ISpeakerIdentityMatcher matcher,
         IOptions<MeetingAssistantOptions> options,
-        ILogger<SpeakerIdentityService> logger)
+        ILogger<SpeakerIdentityService> logger,
+        ISpeakerIdentityMatchValidator matchValidator)
     {
         this.dbContextFactory = dbContextFactory;
         this.snippetExtractor = snippetExtractor;
         this.matcher = matcher;
+        this.matchValidator = matchValidator;
         this.options = options.Value.SpeakerIdentification;
         this.logger = logger;
     }
@@ -198,7 +201,11 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
                 ? suppliedSnippet
                 : await snippetExtractor.ExtractSnippetAsync(
                     request.AudioPath,
-                    group.ToList(),
+                    SpeakerSampleSpanSelector.SelectBestContinuousSpan(
+                        request.Segments,
+                        speaker,
+                        options.MaximumSampleSegmentGap,
+                        options.MinimumSampleSpeechDuration),
                     cancellationToken);
             if (snippet.Length == 0)
             {
@@ -544,6 +551,14 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
 
         foreach (var (speaker, snippet) in unmatchedSpeakers.Where(speaker => speaker.Snippet.Length > 0))
         {
+            if (!await matchValidator.ValidateSampleAsync(snippet, cancellationToken))
+            {
+                logger.LogInformation(
+                    "Skipping speaker identity candidate for {Speaker} because secondary validation rejected the sample",
+                    speaker);
+                continue;
+            }
+
             var now = DateTimeOffset.UtcNow;
             var canonicalName = remainingCandidates.Count == 1 ? remainingCandidates[0] : null;
             var identity = new SpeakerIdentity