24 citations · 114 across the 41 of their papers we have counts for
8 papers · 1 filter
Neural CRF transducers for sequence labeling
Kai Hu, Zhijian Ou, Min Hu +1
Conditional random fields (CRFs) have been shown to be one of the most successful approaches to sequence labeling. Various linear-chain neural CRFs (NCRFs) are developed to impleme…
Elastic CRFs for Open-ontology Slot Filling
Yinpei Dai, Yichi Zhang, Hong Liu +3
Slot filling is a crucial component in task-oriented dialog systems that is used to parse (user) utterances into semantic concepts called slots. An ontology is defined by the colle…
A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
Zhijian Ou
This document aims to provide a review on learning with deep generative models (DGMs), which is an highly-active area in machine learning and more generally, artificial intelligenc…
Improved training of neural trans-dimensional random field language models with dynamic noise-contrastive estimation
Bin Wang, Zhijian Ou
A new whole-sentence language model - neural trans-dimensional random field language model (neural TRF LM), where sentences are modeled as a collection of random fields, and the po…
Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units
Zhangyu Xiao, Zhijian Ou, Wei Chu +1
In this paper, we present an end-to-end automatic speech recognition system, which successfully employs subword units in a hybrid CTC-Attention based system. The subword units are…
Angular Softmax Loss for End-to-end Speaker Verification
Yutian Li, Feng Gao, Zhijian Ou +1
End-to-end speaker verification systems have received increasing interests. The traditional i-vector approach trains a generative model (basically a factor-analysis model) to extra…
Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detection
Yunfu Song, Zhijian Ou
Neural random fields (NRFs), referring to a class of generative models that use neural networks to implement potential functions in random fields (a.k.a. energy-based models), are…
Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning
Yichi Zhang, Zhijian Ou
An ensemble of neural networks is known to be more robust and accurate than an individual network, however usually with linearly-increased cost in both training and testing. In thi…