Pretrained self-supervised speech models can recognize unseen consonants
📄 Pretrained self-supervised speech models can recognize unseen consonants #语音识别 #低资源 #自监督学习 #数据集 6.5/10 | 创新 1/2 | 严谨 1.2/1.5 | 实验 1.2/1.5 | 清晰 1/1 | 影响 0.8/1.5 | 开源 0.3/1.5 | 复现 0.5/0.5 | 工程 0.5/1.5 ✅ 6.5/10 | 前50% | #语音识别 | #自监督学习 | #低资源 #数据集 | arxiv 👥 作者与机构 作者:Chihiro Taguchi, Éric Le Ferrand, Hirosi Nakagawa, Hitomi Ono, Kanji Kato, Emily Prud’hommeaux, David Chiang。 机构:University of Notre Dame, USA; University at Buffalo, USA; Tokyo University of Foreign Studies, Japan; Reitaku University, Japan; Independent researcher; Boston College, USA。 ...