我的应用程序的一个用例是将语音（单个单词的话语）转换为文本。为此，我需要使用 Azure 语音来发短信。有时需要将语音转换为整数 - 例如，我需要将响应作为数量提交。我的问题是无论如何，通过 REST API，告诉语音到文本服务我想要一个数字结果吗？目前它正在返回诸如“one”而不是“1”和“free”而不是“3”之类的东西。我认为文档中没有办法做到这一点，但我想看看其他人是否已经解决了这个问题，然后再想办法解决这个问题。这是我在概念验证项目中使用的代码：
public static async Task SpeechToTextAsync(MemoryStream data, ISpeechResultCallback callBack)
{
string accessToken = await Authentication.GetAccessToken();
IToast toastWrapper = DependencyService.Get<IToast>();
if (accessToken != null)
{
toastWrapper.Show("Acquired token");
callBack.SpeechReturned("Acquired token");
using (var client = new HttpClient())
{
HttpWebRequest request = (HttpWebRequest)HttpWebRequest.Create("https://westus.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=en-GB&format=detailed");
request.SendChunked = true;
request.Accept = @"application/json;text/xml";
request.Method = "POST";
request.ProtocolVersion = HttpVersion.Version11;
request.Host = "westus.stt.speech.microsoft.com";
request.ContentType = @"audio/wav; codecs=audio/pcm; samplerate=16000";
// request.Headers["Ocp-Apim-Subscription-Key"] = Program.SubscriptionKey;
request.Headers.Add("Authorization", "Bearer " + accessToken);
request.AllowWriteStreamBuffering = false;
data.Position = 0;
byte[] buffer = null;
int bytesRead = 0;
using (Stream requestStream = request.GetRequestStream())
{
buffer = new Byte[checked((uint)Math.Min(1024, (int)data.Length))];
while ((bytesRead = data.Read(buffer, 0, buffer.Length)) != 0)
{
requestStream.Write(buffer, 0, bytesRead);
}
// Flush
requestStream.Flush();
}
try
{
string responseData = null;
using (WebResponse response = request.GetResponse())
{
var encoding = Encoding.GetEncoding(((HttpWebResponse)response).CharacterSet);
using (var responseStream = response.GetResponseStream())
{
using (var reader = new StreamReader(responseStream, encoding))
{
responseData = reader.ReadToEnd();
AzureSTTResults deserializedProduct = JsonConvert.DeserializeObject<AzureSTTResults>(responseData);
if(deserializedProduct == null || deserializedProduct.NBest == null || deserializedProduct.NBest.Length == 0)
{
toastWrapper.Show("No results");
callBack.SpeechReturned("No results");
}
else
{
toastWrapper.Show(deserializedProduct.NBest[0].ITN);
callBack.SpeechReturned(deserializedProduct.NBest[0].ITN);
}
}
}
}
}
catch (Exception ex)
{
toastWrapper.Show(ex.Message);
callBack.SpeechReturned(ex.Message);
}
}
}
else
{
toastWrapper.Show("No token required");
callBack.SpeechReturned("No token required");
}
}
这是我想成为“1”的结果示例：
{
"RecognitionStatus": "Success",
"Offset": 0,
"Duration": 22200000,
"NBest": [
{
"Confidence": 0.43084684014320374,
"Lexical": "one",
"ITN": "One",
"MaskedITN": "One",
"Display": "One."
}
]
}