语音到文本转换发音问题。 [英] Speech to text conversion pronunciation problem.

查看:116
本文介绍了语音到文本转换发音问题。的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

我创建了将语音转换为文本的应用程序。

我有使用

I have created application to convert speech to text.
I have use

using System.Speech.Recognition;
using System.Speech.Synthesis;



我正在将英语演讲转换为文本并使用en-US创建语音引擎。


I am converting English speech to text and have use en-US to create speech engine.

private SpeechRecognitionEngine _speechRecognitionEngine = new SpeechRecognitionEngine("en-US");



我使用.net听写语法。


I have use .net dictation grammar.

#region Load .Net defatult grammer.
// Load Dictation Grammer 
DictationGrammar dictationGrammer = new DictationGrammar();
_speechRecognitionEngine.LoadGrammar(dictationGrammer);
#endregion



简要说明我做了什么,除了使用。如上所述,更宽范围的网络听写语法。

我使用相同的代码,如下面的代码项目关联。

C#Speech to Text [ ^ ]

问题域

我住在印度。

人们没有我们的代名词。

当我将表格语音转换成文本时,我得到了无关的转换。

就像当我说美好的一天转换有些事情去吧日。

你可以指导我吗?

您将不胜感激。


To explain in short what I did except that using .net dictation grammar for wider scope as mention above.
I have use same code as following code project articular.
C# Speech to Text[^]
Problem domain
I am staying in India.
People do not have us en pronoun cation.
When i am converting form speech to text I am getting irrelevant conversion.
Like when i say "good day it" convert some thing "go day it".
can you guide me?
You help will be appreciated.

推荐答案

您必须让用户完成语音培训。默认情况下,Windows会受到en-US常用语音的训练,如果您想在另一个重音中使用它,则必须通过训练向导5或6次才能获得更好的STT结果。



http:// windows.microsoft.com/en-us/windows7/set-up-speech-recognition [ ^ ]
You have to have the user go through the speech to text training. By default Windows is trained to the en-US common voice, if you want to use it in another accent, you will have to run through the training wizard 5 or 6 times for better STT results.

http://windows.microsoft.com/en-us/windows7/set-up-speech-recognition[^]


就像已经说过的那样,每个用户必须多次通过此培训向导,机。



但是没有说过的是你永远不会得到完美的结果。 Dragon就是最好的STT发动机,甚至可以达到100%的准确度。
Like has already been said, each user must go through this training wizard multiple times, per machine.

But what hasn''t been said is that you will never get perfect results. Dragon is just about the best STT engine there is and Mr even it can achieve 100% accuracy.


这篇关于语音到文本转换发音问题。的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!

查看全文
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆