Kuaishou Tech
Dec 9, 2021 · Artificial Intelligence
Multi-Task Audio Source Separation (MTASS) and SpeechNAS: AutoML‑Driven Large‑Scale Speaker Recognition
This article presents two ASRU‑2021 accepted works from Kuaishou: MTASS, a multi‑task audio source separation framework that jointly separates speech, music and noise, and SpeechNAS, an AutoML‑based neural architecture search method that achieves state‑of‑the‑art speaker recognition performance with significantly fewer parameters.
AutoMLMTASSNeural Architecture Search
0 likes · 14 min read