From the course: Azure AI Services Essential Training (2023)

Unlock the full course today

Join today to access over 24,200 courses taught by industry experts.

Speaker recognition

Speaker recognition

- [Instructor] Next, let's talk about another amazing capability in Azure Cognitive Services for Speech which is speaker recognition. In speaker recognition, Azure Cognitive Services helps you determine who is speaking a certain audio clip. Now, we do need to make Azure Cognitive Services familiar with who the speaker might be, but we don't need to supply the exact same clip that Azure Cognitive Services has seen before. It could be a brand new clip as long as it belongs to one of the speakers that Azure Cognitive Services has been made aware of. So let's understand the process of how to do this. Here is how it works. First, you create enrollment audios for speakers. Now this enrollment audio is one or more audio clips as long as they amount to about 30 seconds of audio for spoken text. For example, you may have John Doe, Jane Doe. Now John, you need a 30 second audio clip from John and you need another 30 second audio clip…

Contents