期刊
出版社
ISCA-INT SPEECH COMMUNICATION ASSOC
DOI: 10.21437/Interspeech.2018-1417
关键词
speech recognition; acoustic modeling; deep neural networks
类别
资金
- Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA) [FA8650-17-C-9115]
- NSF [CRI-1513128]
Time Delay Neural Networks (TDNNs), also known as one-dimensional Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural network architecture for speech recognition. We introduce a factored form of TDNNs (TDNN-F) which is structurally the same as a TDNN whose layers have been compressed via SVD, but is trained from a random start with one of the two factors of each matrix constrained to be semi-orthogonal. This gives substantial improvements over TDNNs and performs about as well as TDNN-LSTM hybrids.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据