feat: add local Resemblyzer speaker recognition

MeetingAssistant/Speakers/SpeakerIdentityService.cs

@@ -143,7 +143,7 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
 
         target.CanonicalName = targetName;
         target.UpdatedAt = now;
-        ResetCandidates(target, [targetName]);
+        SpeakerIdentityNaming.SetCandidates(target, [targetName]);
         AddMeetingReference(target, meetingReference);
         var snippetAdded = AddSnippetIfNeeded(target, snippet);
         await context.SaveChangesAsync(cancellationToken);
@@ -207,7 +207,7 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
         await using var context = await dbContextFactory.CreateDbContextAsync(cancellationToken);
         await SpeakerIdentitySchema.EnsureCreatedOrUpdatedAsync(context, cancellationToken);
 
-        var attendees = NormalizeAttendees(request.MeetingNote.Frontmatter.Attendees);
+        var attendees = SpeakerIdentityNaming.NormalizeAttendees(request.MeetingNote.Frontmatter.Attendees);
         var meetingReference = CreateReference(request.MeetingNote, DateTimeOffset.UtcNow);
         var speakerMappings = new Dictionary<string, string>(StringComparer.OrdinalIgnoreCase);
         var attendeeMatches = new List<SpeakerIdentityAttendeeMatch>();
@@ -222,7 +222,7 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
             .ToHashSet(StringComparer.OrdinalIgnoreCase);
         foreach (var speaker in request.Segments
             .Select(segment => segment.Speaker)
-            .Where(speaker => !string.IsNullOrWhiteSpace(speaker) && !IsDiarizedSpeakerLabel(speaker)))
+            .Where(speaker => !string.IsNullOrWhiteSpace(speaker) && !SpeakerIdentityNaming.IsDiarizedSpeakerLabel(speaker)))
         {
             alreadyIdentifiedNames.Add(speaker.Trim());
         }
@@ -360,7 +360,7 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
                         cancellationToken);
                 }
 
-                foreach (var acceptedName in GetAcceptedNames(identity))
+                foreach (var acceptedName in SpeakerIdentityNaming.GetAcceptedNames(identity))
                 {
                     matchedAcceptedNames.Add(acceptedName);
                 }
@@ -371,14 +371,14 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
             {
                 speakerMappings[speaker] = speakerName;
                 alreadyIdentifiedNames.Add(speakerName);
-                foreach (var acceptedName in GetAcceptedNames(identity))
+                foreach (var acceptedName in SpeakerIdentityNaming.GetAcceptedNames(identity))
                 {
                     alreadyIdentifiedNames.Add(acceptedName);
                 }
 
                 attendeeMatches.Add(new SpeakerIdentityAttendeeMatch(
                     speakerName,
-                    GetAcceptedNames(identity).ToList()));
+                    SpeakerIdentityNaming.GetAcceptedNames(identity).ToList()));
             }
         }
 
@@ -440,7 +440,7 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
             .Select(identity => new
             {
                 Identity = identity,
-                IsAttendee = MatchesAttendees(identity, attendees),
+                IsAttendee = SpeakerIdentityNaming.MatchesAttendees(identity, attendees),
                 IsActive = identity.UpdatedAt >= activeCutoff
             })
             .Where(candidate => candidate.IsAttendee || candidate.IsActive)
@@ -541,11 +541,11 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
         string operation,
         CancellationToken cancellationToken)
     {
-        var span = SpeakerSampleSpanSelector.SelectBestContinuousSpan(
+        var span = SpeakerSampleSpanSelector.SelectBestSameSpeakerSpan(
             request.Segments,
             speaker,
-            options.MaximumSampleSegmentGap,
-            options.MinimumSampleSpeechDuration);
+            options.MinimumSampleSpeechDuration,
+            options.MaximumSampleDuration);
         logger.LogInformation(
             "{Operation} extracting fallback sample for {Speaker}: selected {SegmentCount} segment(s), span {SpanDuration}, minimum {MinimumDuration}",
             operation,
@@ -569,7 +569,7 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
             .Include(identity => identity.References)
             .ToListAsync(cancellationToken);
         return identities
-            .Where(identity => GetAcceptedNames(identity).Contains(name))
+            .Where(identity => SpeakerIdentityNaming.GetAcceptedNames(identity).Contains(name))
             .OrderBy(identity => string.Equals(identity.CanonicalName, name, StringComparison.OrdinalIgnoreCase) ? 0 : 1)
             .ThenBy(identity => identity.Id)
             .FirstOrDefault();
@@ -589,7 +589,7 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
             .Where(identity => string.IsNullOrWhiteSpace(identity.CanonicalName))
             .ToListAsync(cancellationToken);
         return candidates
-            .Where(identity => identity.References.Any(existing => IsSameReference(existing, reference)))
+            .Where(identity => identity.References.Any(existing => SpeakerIdentityReferences.IsSame(existing, reference)))
             .Where(identity => identity.CandidateNames.Any(candidate =>
                 string.Equals(candidate.Name, targetName, StringComparison.OrdinalIgnoreCase)) ||
                 identity.Aliases.Any(alias =>
@@ -646,27 +646,11 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
         identity.Aliases.Add(new SpeakerAlias { Name = alias.Trim() });
     }
 
-    private static bool IsSameReference(
-        SpeakerIdentityReference first,
-        SpeakerIdentityReference second)
-    {
-        return string.Equals(first.MeetingNotePath, second.MeetingNotePath, StringComparison.OrdinalIgnoreCase) &&
-            string.Equals(first.TranscriptPath, second.TranscriptPath, StringComparison.OrdinalIgnoreCase);
-    }
-
     private static bool MatchesAcceptedNames(
         SpeakerIdentity identity,
         IReadOnlySet<string> names)
     {
-        return GetAcceptedNames(identity).Any(names.Contains);
-    }
-
-    private static bool MatchesAttendees(
-        SpeakerIdentity identity,
-        IReadOnlyList<string> attendees)
-    {
-        var attendeeSet = attendees.ToHashSet(StringComparer.OrdinalIgnoreCase);
-        return GetAcceptedNames(identity).Any(attendeeSet.Contains);
+        return SpeakerIdentityNaming.MatchesAnyAcceptedName(identity, names);
     }
 
     private static Task<SpeakerIdentity?> LoadIdentityAsync(
@@ -694,48 +678,25 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
             var currentCandidates = identity.CandidateNames
                 .Select(candidate => candidate.Name)
                 .ToHashSet(StringComparer.OrdinalIgnoreCase);
-            var fallbackAliasCandidate = currentCandidates.Count == 1 ? currentCandidates.Single() : null;
-            var aliasToCandidate = identity.Aliases
-                .Where(alias => !string.IsNullOrWhiteSpace(alias.Name))
-                .SelectMany(alias => currentCandidates.Select(candidate => new { Alias = alias.Name, Candidate = candidate }))
-                .Where(pair => string.Equals(pair.Alias, pair.Candidate, StringComparison.OrdinalIgnoreCase) ||
-                    pair.Alias.Contains(pair.Candidate, StringComparison.OrdinalIgnoreCase) ||
-                    pair.Candidate.Contains(pair.Alias, StringComparison.OrdinalIgnoreCase))
-                .ToDictionary(pair => pair.Alias, pair => pair.Candidate, StringComparer.OrdinalIgnoreCase);
-            var intersection = attendees
-                .Select(attendee => currentCandidates.Contains(attendee)
-                    ? attendee
-                    : aliasToCandidate.GetValueOrDefault(attendee) ??
-                        (identity.Aliases.Any(alias => string.Equals(alias.Name, attendee, StringComparison.OrdinalIgnoreCase))
-                            ? fallbackAliasCandidate
-                            : null))
-                .Where(candidate => !string.IsNullOrWhiteSpace(candidate))
-                .Select(candidate => candidate!)
-                .Distinct(StringComparer.OrdinalIgnoreCase)
-                .Order(StringComparer.OrdinalIgnoreCase)
-                .ToList();
-
-            if (intersection.Count == 0)
+            var resetToAttendees = SpeakerIdentityNaming.UpdateCandidateNames(identity, attendees);
+            if (resetToAttendees)
             {
                 logger.LogInformation(
                     "Speaker identity candidate elimination for identity {IdentityId} had empty intersection; resetting candidates to attendees {Attendees} and replacing oldest snippet",
                     identity.Id,
                     FormatNames(attendees));
-                ResetCandidates(identity, attendees);
                 ReplaceOldestSnippet(identity, snippet);
                 return;
             }
 
             logger.LogInformation(
-                "Speaker identity candidate elimination for identity {IdentityId}: candidates {CurrentCandidates}, attendees {Attendees}, intersection {Intersection}",
+                "Speaker identity candidate elimination for identity {IdentityId}: candidates {CurrentCandidates}, attendees {Attendees}, remaining {RemainingCandidates}",
                 identity.Id,
                 FormatNames(currentCandidates),
                 FormatNames(attendees),
-                FormatNames(intersection));
-            ResetCandidates(identity, intersection);
-            if (intersection.Count == 1)
+                FormatNames(identity.CandidateNames.Select(candidate => candidate.Name)));
+            if (!string.IsNullOrWhiteSpace(identity.CanonicalName))
             {
-                identity.CanonicalName = intersection[0];
                 logger.LogInformation(
                     "Speaker identity candidate elimination promoted identity {IdentityId} to canonical name {CanonicalName}",
                     identity.Id,
@@ -872,51 +833,6 @@ public sealed class SpeakerIdentityService : ISpeakerIdentificationService
         }
     }
 
-    private static void ResetCandidates(SpeakerIdentity identity, IReadOnlyList<string> candidates)
-    {
-        identity.CandidateNames.Clear();
-        identity.CandidateNames.AddRange(candidates
-            .Distinct(StringComparer.OrdinalIgnoreCase)
-            .Order(StringComparer.OrdinalIgnoreCase)
-            .Select(candidate => new SpeakerCandidateName { Name = candidate }));
-    }
-
-    private static IReadOnlySet<string> GetAcceptedNames(SpeakerIdentity identity)
-    {
-        return new[]
-            {
-                identity.CanonicalName
-            }
-            .Concat(identity.Aliases.Select(alias => alias.Name))
-            .Concat(identity.CandidateNames.Select(candidate => candidate.Name))
-            .Where(name => !string.IsNullOrWhiteSpace(name))
-            .Select(name => name!.Trim())
-            .ToHashSet(StringComparer.OrdinalIgnoreCase);
-    }
-
-    private static IReadOnlyList<string> NormalizeAttendees(IEnumerable<string> attendees)
-    {
-        return attendees
-            .Select(NormalizeAttendee)
-            .Where(attendee => !string.IsNullOrWhiteSpace(attendee))
-            .Distinct(StringComparer.OrdinalIgnoreCase)
-            .Order(StringComparer.OrdinalIgnoreCase)
-            .ToList();
-    }
-
-    private static string NormalizeAttendee(string attendee)
-    {
-        return MeetingAttendeeNames.NormalizeDisplayName(attendee);
-    }
-
-    private static bool IsDiarizedSpeakerLabel(string speaker)
-    {
-        var normalized = speaker.Trim();
-        return normalized.Equals("Unknown", StringComparison.OrdinalIgnoreCase) ||
-            normalized.StartsWith("Guest", StringComparison.OrdinalIgnoreCase) ||
-            normalized.StartsWith("Speaker", StringComparison.OrdinalIgnoreCase);
-    }
-
     private static SpeakerIdentityReference CreateReference(MeetingNote meetingNote, DateTimeOffset timestamp)
     {
         return SpeakerIdentityReferences.Create(