public static AudioInputStream OpenWaveFile(BinaryReader reader)
{
AudioInputStreamFormat format = new AudioInputStreamFormat();
// Tag "RIFF"
char[] data = new char[4];
reader.Read(data, 0, 4);
if (data[0] != 'R' || data[1] != 'I' || data[2] != 'F' || data[3] != 'F')
{
throw new global::System.FormatException("Wrong wav header");
}
// Chunk size
long fileSize = reader.ReadInt32();
// Subchunk, Wave Header
// Subchunk, Format
// Tag: "WAVE"
reader.Read(data, 0, 4);
if ((data[0] != 'W') || (data[1] != 'A') || (data[2] != 'V') || (data[3] != 'E'))
{
throw new global::System.FormatException("Wrong wav tag in wav header");
}
// Tag: "fmt"
reader.Read(data, 0, 4);
if ((data[0] != 'f') || (data[1] != 'm') || (data[2] != 't') && (data[3] != ' '))
{
throw new global::System.FormatException("Wrong format tag in wav header");
}
// chunk format size
long formatSize = reader.ReadInt32();
format.FormatTag = reader.ReadUInt16();
format.Channels = reader.ReadUInt16();
format.SamplesPerSec = (int)reader.ReadUInt32();
format.AvgBytesPerSec = (int)reader.ReadUInt32();
format.BlockAlign = reader.ReadUInt16();
format.BitsPerSample = reader.ReadUInt16();
// Until now we have read 16 bytes in format, the rest is cbSize and is ignored for now.
if (formatSize > 16)
{
reader.ReadBytes((int)(formatSize - 16));
}
// Second Chunk, data
// tag: data.
reader.Read(data, 0, 4);
if ((data[0] != 'd') || (data[1] != 'a') || (data[2] != 't') || (data[3] != 'a'))
{
throw new global::System.FormatException("Wrong data tag in wav");
}
// data chunk size
int dataSize = reader.ReadInt32();
// now, we have the format in the format parameter and the
// reader set to the start of the body, i.e., the raw sample data
return(new BinaryAudioStreamReader(format, reader));
}
public VoiceAudioStream(AudioInputStreamFormat format)
{
// Making the job slightly easier by requiring audio format in the constructor.
// Cognitive Speech services expect:
// - PCM WAV
// - 16k samples/s
// - 32k bytes/s
// - 2 block align
// - 16 bits per sample
// - mono
_format = format;
_dataStream = new EchoStream();
}
private void CreateSpeechClient()
{
var format = new AudioInputStreamFormat()
{
BitsPerSample = 16,
BlockAlign = 2,
AvgBytesPerSec = 32000,
Channels = 1,
FormatTag = 1,
SamplesPerSec = 16000
};
_voiceAudioStream = new VoiceAudioStream(format); // custom AudioInputStream
var factory = SpeechFactory.FromSubscription(_speechKey, _speechRegion);
_speechClient = factory.CreateSpeechRecognizerWithStream(_voiceAudioStream, "en-gb");
_speechClient.RecognitionErrorRaised += _speechClient_RecognitionErrorRaised;
_speechClient.IntermediateResultReceived += _speechClient_IntermediateResultReceived;
_speechClient.FinalResultReceived += _speechClient_FinalResultReceived;
}
