TL;DR本文研究基于知识蒸馏的紧凑深度神经网络模型用于语音识别任务,并通过序列训练和适应进一步提高模型的准确率。在 AMI 会议语音识别语料库上的实验结果表明,该方法显著提高了模型的准确性,同时减小了模型参数规模与识别准确率之间的差距。
Abstract
Deep learning has significantly advanced state-of-the-art of speech
recognition in the past few years. However, compared to conventional Gaussian
mixture acoustic models, neural network models are usually much la