542 citations · 1.3k across the 17 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.SD2020★ 18 cited
FRILL: A Non-Semantic Speech Embedding for Mobile Devices
Jacob Peplinski, Joel Shor, Sachin Joglekar +2
Learned speech representations can drastically improve performance on tasks with limited labeled data. However, due to their size and complexity, learned representations have limit…
eess.AS2020★ 126 cited
Towards Learning a Universal Non-Semantic Representation of Speech
Joel Shor, Aren Jansen, Ronnie Maor +7
The ultimate goal of transfer learning is to reduce labeled data requirements by exploiting a pre-existing embedding model trained for different datasets or tasks. The visual and l…