39 citations · 132 across the 28 of their papers we have counts for
9 papers · 1 filter
Transfer Learning for Speech and Language Processing
Dong Wang, Thomas Fang Zheng
Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trai…
Max-margin Metric Learning for Speaker Recognition
Lantian Li, Dong Wang, Chao Xing +1
Probabilistic linear discriminant analysis (PLDA) is a popular normalization approach for the i-vector model, and has delivered state-of-the-art performance in speaker recognition.…
Binary Speaker Embedding
Lantian Li, Dong Wang, Chao Xing +2
The popular i-vector model represents speakers as low-dimensional continuous vectors (i-vectors), and hence it is a way of continuous speaker embedding. In this paper, we investiga…
Parallel Knowledge Embedding with MapReduce on a Multi-core Processor
Miao Fan, Qiang Zhou, Thomas Fang Zheng +1
This article firstly attempts to explore parallel algorithms of learning distributed representations for both entities and relations in large-scale knowledge repositories with {\it…
Deep Speaker Vectors for Semi Text-independent Speaker Verification
Lantian Li, Dong Wang, Zhiyong Zhang +1
Recent research shows that deep neural networks (DNNs) can be used to extract deep speaker vectors (d-vectors) that preserve speaker characteristics and can be used in speaker veri…
Probabilistic Belief Embedding for Knowledge Base Completion
Miao Fan, Qiang Zhou, Andrew Abel +2
This paper contributes a novel embedding model which measures the probability of each belief in a large-scale knowledge repository via simultaneously learn…
Distant Supervision for Entity Linking
Miao Fan, Qiang Zhou, Thomas Fang Zheng
Entity linking is an indispensable operation of populating knowledge repositories for information extraction. It studies on aligning a textual entity mention to its corresponding d…
Large Margin Nearest Neighbor Embedding for Knowledge Representation
Miao Fan, Qiang Zhou, Thomas Fang Zheng +1
Traditional way of storing facts in triplets ({\it head\_entity, relation, tail\_entity}), abbreviated as ({\it h, r, t}), makes the knowledge intuitively displayed and easily acqu…
Learning Embedding Representations for Knowledge Inference on Imperfect and Incomplete Repositories
Miao Fan, Qiang Zhou, Thomas Fang Zheng
This paper considers the problem of knowledge inference on large-scale imperfect repositories with incomplete coverage by means of embedding entities and relations at the first att…