语音识别及其应用出现“井喷式”发展

在2009-2011年期间，全球语音识别技术普遍转向“深度神经网络”（DNN）平台，DNN架构的层面数量及规模大幅度提升，研究成果频出，出现了“井喷式”发展态势，具体表现在以下8个方面：

1. Scaling up/out and speedup DNN training and decoding;
2. Sequence discriminative training of DNNs;
3. Feature processing by deep models with solid understanding of the underlying mechanisms;
4. Adaptation of DNNs and of related deep models;
5. Multi-task and transfer learning by DNNs and related deep models;
6. Convolution neural networks and how to design them to best exploit domain knowledge of speech;
7. Recurrent neural network and its rich LSTM variants;
8. Other types of deep models including tensor-based models and integrated deep generative/discriminative models.

尤其是近年来，语音识别（SR）技术在社会大众医疗保健、第二外语高效培训、军事航空指挥训练等诸多方面获得成功应用，效果明显。深度神经网络（DNN）技术的具体应用方式是不难想象的，无需多说。百度李彦宏“中国大脑”提案就是在这种“井喷式发展”的大背景下提出的。

袁萌
7月15日

版权声明：本文为博主原创文章，未经博主允许不得转载。