Day 95 – Speaker Voice Verification Using SpeechBrain

We saw a post in previous blogs about SpeechBrain, Features, PreTrained models, Multi-Speaker Speech Separation and Recognition Using SpeechBrain, and Speech Recognition On Different Languages By SpeechBrain.

Today, we are going to see in detail about Speaker Voice Verification?

What is Speaker Voice Verification?

Sometimes, we listen to audios and feel we are hearing same voice on both audios though it’s a different voice on audios.  Speaker voice verification model verifies both speakers are same for the audio and returns True or False.

Let’s get into a code to check simple Speaker Voice Verification.

I have used SpeechBrain Pretrained models and audio files and downloaded mixed audio files (Audacity) from Azure Github.

To check my full code in Google Colab as well as here.

tensor([True]) tensor([0.9691])

tensor([False]) tensor([0.1423])

Have anyone tried SpeechBrain?

Would you please comment below?