9 citations · 30 across the 9 of their papers we have counts for
9 papers
Mutual Information-based Representations Disentanglement for Unaligned Multimodal Language Sequences
Fan Qian, Jiqing Han, Jianchen Li +3
The key challenge in unaligned multimodal language sequences lies in effectively integrating information from various modalities to obtain a refined multimodal joint representation…
Contrastive Loss Based Frame-wise Feature disentanglement for Polyphonic Sound Event Detection
Yadong Guan, Jiqing Han, Hongwei Song +4
Overlapping sound events are ubiquitous in real-world environments, but existing end-to-end sound event detection (SED) methods still struggle to detect them effectively. A critica…
Time-weighted Frequency Domain Audio Representation with GMM Estimator for Anomalous Sound Detection
Jian Guan, Youde Liu, Qiaoxi Zhu +3
Although deep learning is the mainstream method in unsupervised anomalous sound detection, Gaussian Mixture Model (GMM) with statistical audio frequency representation as input can…
A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition
Jiabin Xue, Jiqing Han, Tieran Zheng +2
Recently, data-driven based Automatic Speech Recognition (ASR) systems have achieved state-of-the-art results. And transfer learning is often used when those existing systems are a…
Hard Sample Mining for the Improved Retraining of Automatic Speech Recognition
Jiabin Xue, Jiqing Han, Tieran Zheng +2
It is an effective way that improves the performance of the existing Automatic Speech Recognition (ASR) systems by retraining with more and more new training data in the target dom…
Identifiability of multivariate logistic mixture models
ZiQiang Shi, TieRan Zheng, JiQing Han
Mixture models have been widely used in modeling of continuous observations. For the possibility to estimate the parameters of a mixture model consistently on the basis of observat…
Guarantees of Augmented Trace Norm Models in Tensor Recovery
Ziqiang Shi, Jiqing Han, Tieran Zheng +2
This paper studies the recovery guarantees of the models of minimizing where is a tensor and a…
Online Learning for Classification of Low-rank Representation Features and Its Applications in Audio Segment Classification
Ziqiang Shi, Jiqing Han, Tieran Zheng +1
In this paper, a novel framework based on trace norm minimization for audio segment is proposed. In this framework, both the feature extraction and classification are obtained by s…
Trace Norm Regularized Tensor Classification and Its Online Learning Approaches
Ziqiang Shi, Tieran Zheng, Jiqing Han
In this paper we propose an algorithm to classify tensor data. Our methodology is built on recent studies about matrix classification with the trace norm constrained weight matrix…