feat: add local Resemblyzer speaker recognition

MeetingAssistant/Workflow/WorkflowRulesEditorChatPipeline.cs

@@ -24,6 +24,7 @@ public sealed class WorkflowRulesEditorChatPipeline : IWorkflowRulesEditorChatPi
     private readonly IMeetingMetadataProvider meetingMetadataProvider;
     private readonly ILaunchProfileOptionsProvider launchProfiles;
     private readonly ISpeakerIdentityMergeService identityMergeService;
+    private readonly ResemblyzerVoiceVectorOutlierPruner outlierPruner;
     private readonly AsrDiagnosticService asrDiagnosticService;
     private readonly IConfiguration configuration;
 
@@ -38,6 +39,7 @@ public sealed class WorkflowRulesEditorChatPipeline : IWorkflowRulesEditorChatPi
         IMeetingMetadataProvider meetingMetadataProvider,
         ILaunchProfileOptionsProvider launchProfiles,
         ISpeakerIdentityMergeService identityMergeService,
+        ResemblyzerVoiceVectorOutlierPruner outlierPruner,
         AsrDiagnosticService asrDiagnosticService,
         IConfiguration configuration)
     {
@@ -51,6 +53,7 @@ public sealed class WorkflowRulesEditorChatPipeline : IWorkflowRulesEditorChatPi
         this.meetingMetadataProvider = meetingMetadataProvider;
         this.launchProfiles = launchProfiles;
         this.identityMergeService = identityMergeService;
+        this.outlierPruner = outlierPruner;
         this.asrDiagnosticService = asrDiagnosticService;
         this.configuration = configuration;
     }
@@ -78,7 +81,8 @@ public sealed class WorkflowRulesEditorChatPipeline : IWorkflowRulesEditorChatPi
             identityMergeService,
             asrDiagnosticService,
             configuration,
-            logger: logger);
+            logger: logger,
+            outlierPruner: outlierPruner);
         var messages = conversation
             .Select(ToChatMessage)
             .Append(new ChatMessage(ChatRole.User, userMessage.Trim()))

MeetingAssistant/Workflow/WorkflowRulesEditorTools.cs

@@ -10,6 +10,7 @@ using MeetingAssistant.Transcription;
 using Microsoft.EntityFrameworkCore;
 using Microsoft.Extensions.Configuration;
 using Microsoft.Extensions.Logging;
+using Microsoft.Extensions.Logging.Abstractions;
 using YamlDotNet.Core;
 using YamlDotNet.Serialization;
 
@@ -42,6 +43,7 @@ public sealed class WorkflowRulesEditorTools
     private readonly IMeetingMetadataProvider? meetingMetadataProvider;
     private readonly ILaunchProfileOptionsProvider? launchProfiles;
     private readonly ISpeakerIdentityMergeService? identityMergeService;
+    private readonly ResemblyzerVoiceVectorOutlierPruner outlierPruner;
     private readonly AsrDiagnosticService? asrDiagnosticService;
     private readonly IConfiguration? configuration;
     private readonly ILogger? logger;
@@ -61,7 +63,8 @@ public sealed class WorkflowRulesEditorTools
         string? logDirectory = null,
         string? specRootPath = null,
         string? projectAgentsTemplatePath = null,
-        ILogger? logger = null)
+        ILogger? logger = null,
+        ResemblyzerVoiceVectorOutlierPruner? outlierPruner = null)
     {
         this.options = options;
         rulesPath = WorkflowRulesPathResolver.Resolve(options.Automation.RulesPath);
@@ -82,6 +85,9 @@ public sealed class WorkflowRulesEditorTools
         this.meetingMetadataProvider = meetingMetadataProvider;
         this.launchProfiles = launchProfiles;
         this.identityMergeService = identityMergeService;
+        this.outlierPruner = outlierPruner ?? new ResemblyzerVoiceVectorOutlierPruner(
+            speakerOptions.Resemblyzer,
+            NullLogger<ResemblyzerVoiceVectorOutlierPruner>.Instance);
         this.asrDiagnosticService = asrDiagnosticService;
         this.configuration = configuration;
         this.logger = logger;
@@ -743,8 +749,8 @@ public sealed class WorkflowRulesEditorTools
         string[]? candidateNames = null)
     {
         return Task.FromResult(
-            "Refused: speaker identities require at least one audio sample. " +
-            "Use a speaker override from an existing transcript speaker sample, or update/merge an existing sampled identity.");
+            "Refused: speaker identities require audio evidence (a WAV sample or voice vector). " +
+            "Use a speaker override from an existing transcript speaker, or update/merge an existing identity.");
     }
 
     public async Task<string> UpdateIdentity(
@@ -826,10 +832,12 @@ public sealed class WorkflowRulesEditorTools
                 return $"Could not find target {targetIdentityId} or source {sourceIdentityId}.";
             }
 
-            SpeakerIdentityMerger.MergeInto(
+            SpeakerIdentityMerger.MergeIntoAndPrune(
                 target,
                 source,
-                speakerOptions.MaxSnippetsPerSpeaker);
+                speakerOptions.MaxSnippetsPerSpeaker,
+                speakerOptions.Resemblyzer.MaxVectorsPerIdentity,
+                outlierPruner);
             context.SpeakerIdentities.Remove(source);
             await context.SaveChangesAsync();
             return ToJson(ToIdentityDetail(target));
@@ -1567,9 +1575,11 @@ public sealed class WorkflowRulesEditorTools
     private static IQueryable<SpeakerIdentity> LoadIdentities(SpeakerIdentityDbContext context)
     {
         return context.SpeakerIdentities
+            .AsSplitQuery()
             .Include(identity => identity.Aliases)
             .Include(identity => identity.CandidateNames)
             .Include(identity => identity.Snippets)
+            .Include(identity => identity.VoiceVectors)
             .Include(identity => identity.References);
     }
 
@@ -1591,6 +1601,7 @@ public sealed class WorkflowRulesEditorTools
             identity.Aliases.Select(alias => alias.Name).Order(StringComparer.OrdinalIgnoreCase).ToArray(),
             identity.CandidateNames.Select(candidate => candidate.Name).Order(StringComparer.OrdinalIgnoreCase).ToArray(),
             identity.Snippets.Count,
+            identity.VoiceVectors.Count,
             identity.References.Count,
             identity.UpdatedAt);
     }
@@ -1650,6 +1661,7 @@ public sealed class WorkflowRulesEditorTools
         IReadOnlyList<string> Aliases,
         IReadOnlyList<string> CandidateNames,
         int SampleCount,
+        int VoiceVectorCount,
         int ReferenceCount,
         DateTimeOffset UpdatedAt);