Блог

Желаемая Ситуация

Я хочу слушать звук, исходящий с устройства (ноутбука), и конвертировать его в текст в режиме реального времени (без сохранения в wav-файл).

Текущая Ситуация

Я могу записывать и сохранять выходной звук в wav-файл с помощью NAudio.

Ниже приведен пример кода для сохранения выходных данных в wav-файл. этот код работает нормально

 string outputFileName = @"xxxxxxrecievers.wav";
            var capture = new WasapiLoopbackCapture();
            var writer = new WaveFileWriter(outputFileName, capture.WaveFormat);
            capture.DataAvailable  = async (s, e) =>
            {
                if (writer != null)
                {
                    await writer.WriteAsync(e.Buffer, 0, e.BytesRecorded);
                    await writer.FlushAsync();
                }
            };
            capture.RecordingStopped  = (s, e) =>
            {
                if (writer != null)
                {
                    writer.Dispose();
                    writer = null;
                }
                capture.Dispose();
            };
            capture.StartRecording();
            Console.WriteLine("Record Started, Press Any key to stop the record");
            Console.ReadLine();
            capture.StopRecording();
 

Чтобы преобразовать речь в текст в реальном времени, я пытаюсь переместить буфер в PushAudioStream в следующий пример кода

 public static async Task RecognitionWithPushAudioStreamAsync()
        {
            // Creates an instance of a speech config with specified subscription key and service region.
            // Replace with your own subscription key and service region (e.g., "westus").
            var config = SpeechConfig.FromSubscription("YourSubscriptionKey", "YourServiceRegion");

            var stopRecognition = new TaskCompletionSource<int>();

            // Create a push stream
            using (var pushStream = AudioInputStream.CreatePushStream())
            {
                using (var audioInput = AudioConfig.FromStreamInput(pushStream))
                {
                    // Creates a speech recognizer using audio stream input.
                    using (var recognizer = new SpeechRecognizer(config, audioInput))
                    {
                        // Subscribes to events.
                        recognizer.Recognizing  = (s, e) =>
                        {
                            Console.WriteLine($"RECOGNIZING: Text={e.Result.Text}");
                        };

                        recognizer.Recognized  = (s, e) =>
                        {
                            if (e.Result.Reason == ResultReason.RecognizedSpeech)
                            {
                                Console.WriteLine($"RECOGNIZED: Text={e.Result.Text}");
                            }
                            else if (e.Result.Reason == ResultReason.NoMatch)
                            {
                                Console.WriteLine($"NOMATCH: Speech could not be recognized.");
                            }
                        };

                        recognizer.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 update the subscription info?");
                            }

                            stopRecognition.TrySetResult(0);
                        };

                        recognizer.SessionStarted  = (s, e) =>
                        {
                            Console.WriteLine("nSession started event.");
                        };

                        recognizer.SessionStopped  = (s, e) =>
                        {
                            Console.WriteLine("nSession stopped event.");
                            Console.WriteLine("nStop recognition.");
                            stopRecognition.TrySetResult(0);
                        };

                        // Starts continuous recognition. Uses StopContinuousRecognitionAsync() to stop recognition.
                        await recognizer.StartContinuousRecognitionAsync().ConfigureAwait(false);
                        var capture = new WasapiLoopbackCapture();
                        var writer = new WaveFileWriter(outputFileName, capture.WaveFormat);
                        capture.DataAvailable  = async (s, e) =>
                        {
                            if (writer != null)
                            {
                                await writer.WriteAsync(e.Buffer, 0, e.BytesRecorded);
                                await writer.FlushAsync();
                                pushStream.Write(e.Buffer, e.BytesRecorded); // try to push buffer here
                            }
                        };
                        capture.RecordingStopped  = (s, e) =>
                        {
                            if (writer != null)
                            {
                                writer.Dispose();
                                writer = null;
                            }
                            capture.Dispose();
                        };
                        capture.StartRecording();
                        Console.WriteLine("Record Started, Press Any key to stop the record");
                        Console.ReadLine();
                        capture.StopRecording();
                        pushStream.Close();

                        // Waits for completion.
                        // Use Task.WaitAny to keep the task rooted.
                        Task.WaitAny(new[] { stopRecognition.Task });

                        // Stops recognition.
                        await recognizer.StopContinuousRecognitionAsync().ConfigureAwait(false);
                    }
 

in short I am opening a pushstream like

 using (var pushStream = AudioInputStream.CreatePushStream())
 

и пытается протолкнуть буфер в поток, как

 pushStream.Write(e.Buffer, e.BytesRecorded);
 

Не удается распознать речь с помощью когнитивной службы.

Заранее спасибо за помощь