In this video, learn about the basic theory behind speaker recognition and a discussion of major concepts.
- [Instructor] Next let's talk about speaker recognition.…As the name suggests, speaker recognition is the ability…of a computer to listen to a voice…and identify who the voice belongs to.…And there are two parts to this.…They're very similar.…One is called identification…where you pass in a sample audio spoken text…and the computer tells you who that speaker is.…And the second is one step above that…where you can use the voice…for authentication or verification…where the phrase you speak…along with the identity of the speaker,…both need to be correct…for an authentication to be performed.…
Now before we dive into the nitty gritty of code,…let's understand exactly what I intend to do.…The process of speaker recognition…first involves enrolling a speaker.…This means you create an identification profile…and on their identification profile you enroll…at least 30 seconds of audio of that person,…not including silence.…You can do so using multiple files,…as in, if you upload a single file…of 15 seconds in length,…the computer will tell you…
- 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
Skill Level Advanced
Creating Bots with the Microsoft Bot Framework, Part 1with Scott Peterson45m 41s Intermediate
Learning Microsoft Cognitive Services for Developerswith Sahil Malik1h 42m Intermediate
1. The Basics
2. Translation Text API
3. Bing Speech API
4. Speaker Recognition API
Next steps1m 9s
- Mark as unwatched
- Mark all as unwatched
Are you sure you want to mark all the videos in this course as unwatched?
This will not affect your course history, your reports, or your certificates of completion for this course.Cancel
Take notes with your new membership!
Type in the entry box, then click Enter to save your note.
1:30Press on any video thumbnail to jump immediately to the timecode shown.
Notes are saved with you account but can also be exported as plain text, MS Word, PDF, Google Doc, or Evernote.