Azure TTS Speaker Separation Problem

I am using the Python code to do realtime transcription with diarization. It always calls cancel event. Its a paid subscription with .wav file.

Canceled event

CLOSING on ConversationTranscriptionCanceledEventArgs(session_id=f39fc4e1b4ee48018ff9ef5af4f096ad, result=ConversationTranscriptionResult(result_id=63fe01d9b3be498bb263fc72ccdba7b1, speaker_id=, text=, reason=ResultReason.Canceled))

Hi JW J

Please share the code and details for repro.

Thank You.

Hi JW J

Did you get any chance to check above response

Thank You.

Hello,

I apologize for the late reply; I was away on a business trip.

Due to this board’s policy, I can’t upload zip files, so I’m only posting the source code. Once you create a console application, you can simply copy and paste this code, and it should run correctly.

Please note that the key and region used in the source code are currently from a paid plan on Azure.

Thank you for your help.

using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Audio;
using Microsoft.CognitiveServices.Speech.Transcription;

class Program
{
    // This example requires environment variables named "SPEECH_KEY" and "SPEECH_REGION"
    static string speechKey = "ab33811cea1243fb94c45749ec2cc03c";
    static string speechRegion = "eastus";
    async static Task Main(string[] args)
    {
        string baseDir = AppContext.BaseDirectory;
        // 그 안에 복사된 mp3 파일 경로
        string filepath = Path.Combine(baseDir, "test.mp3");
        Console.WriteLine($"MP3 fullPath: {filepath}");
        var speechConfig = SpeechConfig.FromSubscription(speechKey, speechRegion);
        speechConfig.SpeechRecognitionLanguage = "ko-KR";
        speechConfig.SetProperty(PropertyId.SpeechServiceResponse_DiarizeIntermediateResults, "true");
        var stopRecognition = new TaskCompletionSource<int>(TaskCreationOptions.RunContinuationsAsynchronously);
        // Create an audio stream from a wav file or from the default microphone
        using (var audioConfig = AudioConfig.FromWavFileInput(filepath))
        {
            // Create a conversation transcriber using audio stream input
            using (var conversationTranscriber = new ConversationTranscriber(speechConfig, audioConfig))
            {
                conversationTranscriber.Transcribing += (s, e) =>
                {
                    Console.WriteLine($"TRANSCRIBING: Text={e.Result.Text} Speaker ID={e.Result.SpeakerId}");
                };
                conversationTranscriber.Transcribed += (s, e) =>
                {
                    if (e.Result.Reason == ResultReason.RecognizedSpeech)
                    {
                        Console.WriteLine();
                        Console.WriteLine($"TRANSCRIBED: Text={e.Result.Text} Speaker ID={e.Result.SpeakerId}");
                        Console.WriteLine();
                    }
                    else if (e.Result.Reason == ResultReason.NoMatch)
                    {
                        Console.WriteLine($"NOMATCH: Speech could not be transcribed.");
                    }
                };
                conversationTranscriber.Canceled += (s, e) =>
                {
                    Console.WriteLine($"CANCELED: Reason={e.Reason}");
                    if (e.Reason == CancellationReason.Error)
                    {
                        Console.WriteLine($"CANCELED: ErrorCode={e.ErrorCode}");
                        Console.WriteLine($"CANCELED: ErrorDetails={e.ErrorDetails}");
                        Console.WriteLine($"CANCELED: Did you set the speech resource key and region values?");
                        stopRecognition.TrySetResult(0);
                    }
                    stopRecognition.TrySetResult(0);
                };
                conversationTranscriber.SessionStopped += (s, e) =>
                {
                    Console.WriteLine("\n    Session stopped event.");
                    stopRecognition.TrySetResult(0);
                };
                await conversationTranscriber.StartTranscribingAsync();
                // Waits for completion. Use Task.WaitAny to keep the task rooted.
                Task.WaitAny(new[] { stopRecognition.Task });
                await conversationTranscriber.StopTranscribingAsync();
            }
        }
    }
}