...Qian-Bei Hong; Chung-Hsien Wu; Hsin-Min Wang This paper proposes a novel speaker-specific articulatory feature (AF) extraction model based on knowledge distillation (KD) for speaker recognition. First, an AF extractor is trained as a teacher model for extracting the AF profiles of the input speaker...

... to make the student model find a wider robust minimum. Finally, we propose the offline ensemble pre-trained teachers to teach a student model. To address dimension mismatch between teacher and student models, we adopt a 1 × 1 convolution and two-stage knowledge distillation to release...