KwangHee Choi, Ankita Pasad, Tomohiko Nakamura, Satoru Fukayama, Karen Livescu, Shinji Watanabe 0001. Self-Supervised Speech Representations are More Phonetic than Semantic. In Itshak Lapidot, Sharon Gannot, editors, 25th Annual Conference of the International Speech Communication Association, Interspeech 2024, Kos, Greece, September 1-5, 2024. ISCA, 2024. [doi]
Abstract is missing.