DEEP NEURAL SUPPORT VECTOR MACHINES - MICROSOFT TECHNOLOGY LICENSING LLC

Title:

DEEP NEURAL SUPPORT VECTOR MACHINES

Document Type and Number:

WIPO Patent Application WO/2016/165120

Kind Code:

A1

Abstract:

Aspects of the technology described herein relates to a new type of deep neural network (DNN). The new DNN is described herein as a deep neural support vector machine (DNSVM). Traditional DNNs use the multinomial logistic regression (softmax activation) at the top layer and underlying layers for training. The new DNN instead uses a support vector machine (SVM) as one or more layers, including the top layer. The technology described herein can use one of two training algorithms to train the DNSVM to learn parameters of SVM and DNN in the maximum-margin criteria. The first training method is a frame-level training. In the frame-level training, the new model is shown to be related to the multiclass SVM with DNN features. The second training method is the sequence-level training. The sequence-level training is related to the structured SVM with DNN features and HMM state transition features.

More Like This:

JP2004510206	Features for pattern matching Pretreatment method
JPS6273300	VOICE PATTERN MATCHING SYSTEM
JPH06161495	SPEECH RECOGNIZING DEVICE

Inventors:

ZHANG SHIXIONG (CN)
LIU CHAOJUN (US)
YAO KAISHENG (US)
GONG YIFAN (US)

Application Number:

PCT/CN2015/076857

Publication Date:

October 20, 2016

Filing Date:

April 17, 2015

Export Citation:

Click for automatic bibliography generation Help

Assignee:

MICROSOFT TECHNOLOGY LICENSING LLC (US)
ZHANG SHIXIONG (CN)
LIU CHAOJUN (US)
YAO KAISHENG (US)
GONG YIFAN (US)

International Classes:

G10L15/02

Foreign References:

US20150095027A1	2015-04-02
US20050033574A1	2005-02-10
US20150032449A1	2015-01-29
US20140257805A1	2014-09-11
US8484022B1	2013-07-09
CN1783213A	2006-06-07

Other References: