2 papers
cs.CL2025
Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices
Evan King, Adam Sabra, Manjunath Kudlur +2
We present the Flavors of Moonshine, a suite of tiny automatic speech recognition (ASR) models specialized for a range of underrepresented languages. Prevailing wisdom suggests tha…
cs.SD2024
SECP: A Speech Enhancement-Based Curation Pipeline For Scalable Acquisition Of Clean Speech
Adam Sabra, Cyprian Wronka, Michelle Mao +1
As more speech technologies rely on a supervised deep learning approach with clean speech as the ground truth, a methodology to onboard said speech at scale is needed. However, thi…