Haotian Xu

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
Recently, distributed word embeddings trained by neural language models are commonly used for text classification with Convolutional Neural Networks (CNNs). In this paper, we propose a novel neural language model, Topic-based Skip-gram, to learn topic-based word embeddings for biomedical literature indexing with CNNs. Topic-based Skip-gram leverages textual(More)
In this paper, we study the scalable discovery of audio repetitive patterns/motifs in long broadcast streams, where two segments are said to be repetitive if their audio fingerprints are close to each other. In this task, as we are confined to handle limited variability, we can adapt an audio hashing technique, originally proposed for searching a given(More)
Though with progress, model learning and performing posterior inference still remains a common challenge for using deep generative models, especially for handling discrete hidden variables. This paper is mainly concerned with algorithms for learning Helmholz machines, which is characterized by pairing the genera-tive model with an auxiliary inference model.(More)
State-of-the-art i-vector based speaker verification relies on variants of Probabilistic Linear Discriminant Analysis (PLDA) for dis-criminant analysis. We are mainly motivated by the recent work of the joint Bayesian (JB) method, which is originally proposed for discriminant analysis in face verification. We apply JB to speaker verification and make three(More)
Personal Imagine being plunged perpetually into a silence where the ubiquity of sound is irrelevant. That is the world which many students in my high school experience. My inspiration for this project really came from the students in my high school's Deaf and Hard of Hearing (DHH) program. My school has a department which offers a high school education to(More)
  • 1