PaperDecision tree-based acoustic models for speech recognition with improved smoothnessMasami Akamine, Jitendra AjmeraIEICE Trans Inf Syst
Conference paperFrom modern standard Arabic to Levantine ASR: Leveraging GALE for dialectsHagen Soltau, Lidia Mangu, et al.ASRU 2011
Conference paper∆-encoder: an effective sample synthesis method for few-shot object recognitionEli Schwartz, Leonid Karlinsky, et al.NeurIPS 2018