Harden speaker identity samples

MeetingAssistant/Speakers/SpeakerCompositeWav.cs

@@ -0,0 +1,107 @@
+using MeetingAssistant.Transcription;
+using NAudio.Wave;
+
+namespace MeetingAssistant.Speakers;
+
+internal static class SpeakerCompositeWav
+{
+    public static WaveFileReader? OpenFirstReadableWave(IEnumerable<byte[]> snippets)
+    {
+        foreach (var bytes in snippets)
+        {
+            if (bytes.Length == 0)
+            {
+                continue;
+            }
+
+            try
+            {
+                return new WaveFileReader(new MemoryStream(bytes));
+            }
+            catch (FormatException)
+            {
+            }
+        }
+
+        return null;
+    }
+
+    public static TimeSegment? AppendSnippet(
+        WaveFileWriter writer,
+        WaveFormat targetFormat,
+        byte[] snippet,
+        TimeSpan start)
+    {
+        if (snippet.Length == 0)
+        {
+            return null;
+        }
+
+        using var reader = new WaveFileReader(new MemoryStream(snippet));
+        if (!WaveFormatsMatch(reader.WaveFormat, targetFormat))
+        {
+            throw new InvalidDataException("Speaker identity snippets must use the same WAV format.");
+        }
+
+        reader.CopyTo(writer);
+        return new TimeSegment(start, start + reader.TotalTime);
+    }
+
+    public static void WriteSilence(
+        WaveFileWriter writer,
+        WaveFormat format,
+        TimeSpan duration)
+    {
+        if (duration <= TimeSpan.Zero)
+        {
+            return;
+        }
+
+        var bytes = new byte[(int)(format.AverageBytesPerSecond * duration.TotalSeconds)];
+        writer.Write(bytes, 0, bytes.Length);
+    }
+
+    public static string? FindBestSpeaker(
+        TimeSegment segment,
+        IReadOnlyList<TranscriptionSegment> segments)
+    {
+        var bestOverlap = 0d;
+        string? bestSpeaker = null;
+        foreach (var transcriptSegment in segments)
+        {
+            var overlap = Math.Min(segment.End.TotalSeconds, transcriptSegment.End.TotalSeconds)
+                - Math.Max(segment.Start.TotalSeconds, transcriptSegment.Start.TotalSeconds);
+            if (overlap > bestOverlap)
+            {
+                bestOverlap = overlap;
+                bestSpeaker = transcriptSegment.Speaker;
+            }
+        }
+
+        return bestSpeaker;
+    }
+
+    public static void TryDelete(string path)
+    {
+        try
+        {
+            if (File.Exists(path))
+            {
+                File.Delete(path);
+            }
+        }
+        catch (IOException)
+        {
+        }
+    }
+
+    private static bool WaveFormatsMatch(WaveFormat left, WaveFormat right)
+    {
+        return left.Encoding == right.Encoding
+            && left.SampleRate == right.SampleRate
+            && left.Channels == right.Channels
+            && left.BitsPerSample == right.BitsPerSample;
+    }
+}
+
+internal readonly record struct TimeSegment(TimeSpan Start, TimeSpan End);