Recognizing a Million Voices: Low Dimensional Audio Representations for Speaker Identification

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Teaches low-dimensional audio representations for speaker identification at scale, demonstrating signal processing and machine learning. Covers specific technique for audio analysis.

A 111-minute video from Microsoft Research: “Recognizing a Million Voices: Low Dimensional Audio Representations for Speaker Identification”.

Video by Microsoft Research, played through YouTube's embedded player.

Part of Audio & Acoustics