Google Web Speech API 中的语法
我可以通过给他一个单词列表(在我的例子中,用户的请求是非常可预测的)来改进Google语音API识别,以使识别更加准确吗?
Can I improve Google speech API recognition by give him a words list (in my case the request of user is very predictable) to make recognition more accurate?
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(3)
正确答案是:不,你不能。 =(
Correct answer is: no, you can't. =(
我不能代表 Chrome,但在 Android 中,他们很清楚你无法提供语法。在 Android 语音识别中,您只能选择两种模型:“自由形式”和“网络搜索”。
请参阅 Android:语音识别附加字典?
I can't speak for Chrome, but in Android they are quite clear that you cannot provide a grammar. In Android speech recognition you are limited to a choice of two models: "free form" and "web search".
See Android: Speech Recognition Append Dictionary?
对于 Google Cloud Speech API(不是 Web Speech API),但有些人可能会发现这很有用:
虽然目前处于测试阶段,但 Google 已经发布了新功能,允许您
请参阅 https://cloud.google.com/speech-to-text/docs/context-strength
For Google Cloud Speech API (Not Web Speech API) but some may find this useful:
Although currently in beta, Google has released new capability which allows you to
See https://cloud.google.com/speech-to-text/docs/context-strength