Yossi Keshet
@keshet.bsky.social
Speech, language, and deep learning at the Technion. But also psychology, philosophy, and history. And Jazz improv.
Reposted by Yossi Keshet
Really excited to share "A perceptual similarity space for speech based on self-supervised speech representations" w/ B. R. Chernyak, A. Bradlow, @keshet.bsky.social Open access at JASA pubs.aip.org/asa/jasa/art... Supported by NSF BCS program 1/5
A perceptual similarity space for speech based on self-supervised speech representations
Speech recognition by both humans and machines frequently fails in non-optimal yet common situations. For example, word recognition error rates for second-langu
pubs.aip.org
June 21, 2024 at 2:51 PM
Really excited to share "A perceptual similarity space for speech based on self-supervised speech representations" w/ B. R. Chernyak, A. Bradlow, @keshet.bsky.social Open access at JASA pubs.aip.org/asa/jasa/art... Supported by NSF BCS program 1/5