Lecture Series in Pattern Recognition
题 目 (TITLE)：Deep Learning for Speech and Language Processing
讲 座 人 (SPEAKER)：Prof. Dong Yu (Microsoft Research)
主 持 人 (CHAIR)：Prof. Bo Xu
时 间 (TIME)： October 23(Wedsday), 2013, 9:00 AM
地 点 (VENUE)：No.2 Conference Room (3rd floor), Intelligence Building
Recently, deep learning techniques have been successfully applied to speech recognition, image recognition, and some natural language processing tasks and became the new state-of-the-art in these fields. In this talk, I will discuss some recent advances of deep learning in speech and language processing. I will use example applications to show how deep learning can be applied to solve real-world problems and why it works so well in practice.
Dr. Dong Yu is a principal researcher at Microsoft Research. His research interests span speech processing, robust speech recognition, discriminative training, and machine learning. He has published over 120 papers in these areas and is the inventor/coinventor of more than 50 granted/pending patents.
His most recent work focuses on deep learning and its application in large vocabulary speech recognition. The context-dependent deep neural network hidden Markov model (CD-DNN-HMM) he co-proposed and developed has been seriously challenging the dominant position of the conventional GMM based system for large vocabulary speech recognition.