如何在识别之前获取输入语音
如何在识别之前获取输入语音。 例如,如果我说“hel”,它在字典中找不到它。或者它认为它是另一个词。 我只是想得到“he”
how to get the input speech before it was recognized.
for example if I say "hel," and it does not find it in dictionary .or it thinks its another word .
I just want to get the "hel"
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论
评论(1)
您需要提供更多详细信息。您使用什么语音转文本系统?您目前如何访问它?您希望输入语音采用什么格式? (声波?可能的音素网格?最可能的音素序列?等等)
You need to supply more details. What speech-to-text system are you using? How are you currently accessing it? What format do you want the input speech in? (Sound wave? Lattice of possible phonemes? Most likely sequence of phonemes? Etc.)