Get a basic introduction to the speech part of Microsoft Cognitive Services. This video discusses the various capabilities that are discussed in this course.
- [Instructor] Welcome to Microsoft Cognitive Services, Speech. Speech. Isn't that what you're listening to right now? We are talking with each other, aren't we? Well, the reality is that the vast majority of communication between us humans is based on speech. Speech. We talk in so many different languages with each other. We express so many different emotions. There are so many people that talk with us. There is so much that is embedded inside of speech.
In the way I'm talking, I might be expressing surprise, anger, or so much more. But then the reality is that the speech we express is in so many different languages and cultures, and expands so many different people that one thing that may have a certain negative meaning in a certain part of the world may not be as negative in another? Certainly. Or have you ever run into a situation where multiple people are talking at the same time, and you can't seem to understand any one of them? Or perhaps you want to recognize who is who just based on the audio.
Microsoft Cognitive Services lets you translate between multiple languages. Yes, somebody could be speaking Chinese, but with the help of Microsoft Cognitive Services, you can understand them in a language you understand. Microsoft Cognitive Services also lets you convert your speech to text, or text to speech. Wouldn't it be amazing, if you were listening to this course, and it came with a transcript that you could search through? I think you can already do that, but that's because that transcript is text you can search in.
Microsoft Cognitive Services also lets you detect who the speaker is. This would be amazing in the case of identification, as in, think military. You're listening to some audio on a wireless conversation, and you want to know who that person is, that is talking on the wireless tap audio. Or perhaps for authentication, where you can unlock a door by simply talking to it. Then yes, as I mentioned, Microsoft Cognitive Services also lets you verify the speaker.
Yes, you can now use your voice for authentication in your house. This is extremely powerful. Imagine, on mobile devices, wouldn't it be nice if you can unlock an application by simply talking to it? This, and many other possibilities. So let's together learn Microsoft Cognitive Services, Speech.
- Using the Translate Text API
- Getting supported languages
- Writing code to translate between languages
- Performing text to speech
- Setting up speech to text
- Writing code for speaker identification