no code implementations • NAACL 2022 • Hao Huang, Xiubo Geng, Guodong Long, Daxin Jiang
Precise question understanding is critical for temporal reading comprehension.
no code implementations • 29 Nov 2023 • Yuhang Yang, Yizhou Peng, Xionghu Zhong, Hao Huang, Eng Siong Chng
The Mixed Error Rate results show that the amount of adaptation data may be as low as $1\sim10$ hours to achieve saturation in performance gain (SEAME) while the ASRU task continued to show performance with more adaptation data ($>$100 hours).
no code implementations • 17 Nov 2023 • Xiaojiao Chen, Sheng Li, Jiyi Li, Hao Huang, Yang Cao, Liang He
This paper demonstrates that an attacker can extract speaker information by querying speaker-adapted speech recognition (ASR) systems.
no code implementations • 17 Nov 2023 • Xiaojiao Chen, Sheng Li, Jiyi Li, Hao Huang, Yang Cao, Liang He
Current speaker anonymization methods, especially with self-supervised learning (SSL) models, require massive computational resources when hiding speaker identity.
no code implementations • 31 Oct 2023 • Yu Hao, Fan Yang, Hao Huang, Shuaihang Yuan, Sundeep Rangan, John-Ross Rizzo, Yao Wang, Yi Fang
By combining the prompt and input image, a large vision-language model (i. e., InstructBLIP) generates detailed and comprehensive descriptions of the environment and identifies potential risks in the environment by analyzing the environmental objects and scenes, relevant to the prompt.
1 code implementation • 20 Aug 2023 • Ji Zhang, Lianli Gao, Bingguang Hao, Hao Huang, Jingkuan Song, HengTao Shen
Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
no code implementations • 19 Aug 2023 • Xiaoyu Ye, Hao Huang, Jiaqi An, Yongtao Wang
Stable Diffusion (SD) customization approaches enable users to personalize SD model outputs, greatly enhancing the flexibility and diversity of AI art.
no code implementations • 23 May 2023 • Zhibin Qiu, Mengfan Fu, Fuchun Sun, Gulila Altenbek, Hao Huang
Our experiments on multiple datasets demonstrate the effectiveness of SE-Bridge in SE.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
no code implementations • ICCV 2023 • Kaixun Jiang, Zhaoyu Chen, Hao Huang, Jiafeng Wang, Dingkang Yang, Bo Li, Yan Wang, Wenqiang Zhang
First, STDE introduces target videos as patch textures and only adds patches on keyframes that are adaptively selected by temporal difference.
no code implementations • 7 Mar 2023 • Hao Huang, Katherine R. Davis, H. Vincent Poor
The RECO of resilient ecosystems favors a balance of food webs' network efficiency and redundancy.
no code implementations • 16 Feb 2023 • Jinkuan Zhu, Hao Huang, Qiao Deng, Xiyao Li
In this paper, we propose a novel fashion image retrieval method leveraging both global and fine-grained features, dubbed Multi-Granular Alignment (MGA).
Ranked #3 on
Metric Learning
on In-Shop
1 code implementation • CVPR 2023 • Hao Huang, Ziyan Chen, Huanran Chen, Yongtao Wang, Kevin Zhang
Then, we analogize patch optimization with regular model optimization, proposing a series of self-ensemble approaches on the input data, the attacked model, and the adversarial patch to efficiently make use of the limited information and prevent the patch from overfitting.
1 code implementation • 1 Nov 2022 • Yuhang Yang, HaiHua Xu, Hao Huang, Eng Siong Chng, Sheng Li
To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and language (aka text data); 2) the homogeneity of the learned representations from two encoders.
no code implementations • 9 Jul 2022 • Jicheng Zhang, Yizhou Peng, HaiHua Xu, Yi He, Eng Siong Chng, Hao Huang
Intermediate layer output (ILO) regularization by means of multitask training on encoder side has been shown to be an effective approach to yielding improved results on a wide range of end-to-end ASR frameworks.
no code implementations • 9 Jul 2022 • Yizhou Peng, Yufei Liu, Jicheng Zhang, HaiHua Xu, Yi He, Hao Huang, Eng Siong Chng
More importantly, we train an end-to-end (E2E) speech recognition model by means of merging two monolingual data sets and observe the efficacy of the proposed ILME-based LM fusion for CSSR.
no code implementations • 3 Jul 2022 • Ying Hu, Yuwu Tang, Hao Huang, Liang He
Speech emotion recognition (SER) is an essential part of human-computer interaction.
no code implementations • IEEE Signal Processing Letters 2022 • Ying Hu, Yadong Chen, Wenzhong Yang, Liang He, Hao Huang
In this paper, we propose a model which combines the complexed spectrogram domain feature and time-domain feature by a cross-domain encoder (CDE) and adopts the hierarchic temporal convolutional network (HTCN) for multiple music sources separation.
Ranked #8 on
Music Source Separation
on MUSDB18
3 code implementations • 13 Jun 2022 • Luca Gagliardi, Andrea Raffo, Ulderico Fugacci, Silvia Biasotti, Walter Rocchia, Hao Huang, Boulbaba Ben Amor, Yi Fang, Yuanyuan Zhang, Xiao Wang, Charles Christoffer, Daisuke Kihara, Apostolos Axenopoulos, Stelios Mylonas, Petros Daras
This paper presents the methods that have participated in the SHREC 2022 contest on protein-ligand binding site recognition.
1 code implementation • 8 Apr 2022 • Qianying Liu, Zhuo Gong, Zhengdong Yang, Yuhang Yang, Sheng Li, Chenchen Ding, Nobuaki Minematsu, Hao Huang, Fei Cheng, Chenhui Chu, Sadao Kurohashi
Low-resource speech recognition has been long-suffering from insufficient training data.
1 code implementation • CVPR 2022 • Xinyu Lyu, Lianli Gao, Yuyu Guo, Zhou Zhao, Hao Huang, Heng Tao Shen, Jingkuan Song
The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e. g., "woman-on/standing on/walking on-beach" or "woman-near/looking at/in front of-child".
1 code implementation • 14 Mar 2022 • Xin Fan, Zi Li, Ziyang Li, Xiaolin Wang, Risheng Liu, Zhongxuan Luo, Hao Huang
Deformable image registration plays a critical role in various tasks of medical image analysis.
no code implementations • 13 Dec 2021 • Guodong Ma, Pengfei Hu, Nurmemet Yolwas, Shen Huang, Hao Huang
To boost the performance of PMT, we propose multi-modeling unit training (MMUT) architecture fusion with PMT (PM-MMUT).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
no code implementations • 27 Oct 2021 • Pengyi Yang, Hao Huang, Chunlei Liu
Feature selection techniques are essential for high-dimensional data analysis.
no code implementations • 20 Oct 2021 • Giulia Pedrielli, Tanmay Kandhait, Surdeep Chotaliya, Quinn Thibeault, Hao Huang, Mauricio Castillo-Effen, Georgios Fainekos
Requirements driven search-based testing (also known as falsification) has proven to be a practical and effective method for discovering erroneous behaviors in Cyber-Physical Systems.
no code implementations • 7 Oct 2021 • Yizhou Peng, Jicheng Zhang, HaiHua Xu, Hao Huang, Eng Siong Chng
Non-autoregressive end-to-end ASR framework might be potentially appropriate for code-switching recognition task thanks to its inherent property that present output token being independent of historical ones.
no code implementations • ICLR 2022 • Hao Huang, Yi Fang
We present a novel method for 3D shape representation learning using multi-scale wavelet decomposition.
no code implementations • 21 Sep 2021 • Mengxi Wu, Hao Huang, Yi Fang
In contrast to the PGD-k attack, our method generates adversarial samples that keep the geometric features in clean samples and contain few outliers.
no code implementations • ACL 2021 • Hao Huang, Xiubo Geng, Jian Pei, Guodong Long, Daxin Jiang
Procedural text understanding aims at tracking the states (e. g., create, move, destroy) and locations of the entities mentioned in a given paragraph.
no code implementations • 13 Jul 2021 • Hao Huang, Zeyu Mao, Varuneswara Panyam, Astrid Layton, Katherine Davis
Power systems are critical infrastructure for reliable and secure electric energy delivery.
no code implementations • 22 Jun 2021 • Hao Huang, Boulbaba Ben Amor, Xichan Lin, Fan Zhu, Yi Fang
In this work, we introduce a joint geometric-neural networks approach for comparing, deforming and generating 3D protein structures.
no code implementations • 22 Jun 2021 • Hao Huang, Boulbaba Ben Amor, Xichan Lin, Fan Zhu, Yi Fang
Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings.
no code implementations • 15 Jun 2021 • Jicheng Zhang, Yizhou Peng, Pham Van Tung, HaiHua Xu, Hao Huang, Eng Siong Chng
In this paper, we propose a single multi-task learning framework to perform End-to-End (E2E) speech recognition (ASR) and accent recognition (AR) simultaneously.
1 code implementation • 23 May 2021 • Hao Huang, Yongtao Wang, Zhaoyu Chen, Yuze Zhang, Yuheng Li, Zhi Tang, Wei Chu, Jingdong Chen, Weisi Lin, Kai-Kuang Ma
Then, we design a two-level perturbation fusion strategy to alleviate the conflict between the adversarial watermarks generated by different facial images and models.
1 code implementation • 23 Mar 2021 • Hao Huang, Yongtao Wang, Zhaoyu Chen, Zhi Tang, Wenqiang Zhang, Kai-Kuang Ma
Firstly, we propose a patch selection and refining scheme to find the pixels which have the greatest importance for attack and remove the inconsequential perturbations gradually.
no code implementations • 16 Feb 2021 • Hao Huang, Zeyu Mao, Mohammad Rasoul Narimani, Katherine R. Davis
Based on each selected branch, the approach constructs the subgraph with parameters of distance and search level, while using branches' LODF metrics as the weights.
no code implementations • 18 Jan 2021 • Abhijeet Sahu, Zeyu Mao, Patrick Wlazlo, Hao Huang, Katherine Davis, Ana Goulart, Saman Zonouz
We perform multi-source data fusion for training IDS in a cyber-physical power system testbed where we collect cyber and physical side data from multiple sensors emulating real-world data sources that would be found in a utility and synthesizes these into features for algorithms to detect intrusions.
no code implementations • 15 Jan 2021 • Hao Huang, C. Matthew Davis, Katherine R. Davis
The usage and configuration of DNP3 with real-world equipment in to achieve power system monitoring and control of a large-scale synthetic electric grid via this DNP3 communication is presented.
no code implementations • 30 Oct 2020 • Hao Huang, Varuneswara Panyam, Mohammad Rasoul Narimani, Astrid Layton, Katherine R. Davis
This paper presents an approach to address this challenge through bio-inspired power system network design to improve system reliability and resilience against disturbances.
no code implementations • 30 Oct 2020 • Wonhyeok Jang, Hao Huang, Katherine R. Davis, Thomas J. Overbye
Power system restoration is a highly complex task that must be performed in a timely manner following a blackout.
no code implementations • 22 Oct 2020 • Yizhou Peng, Jicheng Zhang, Haobo Zhang, HaiHua Xu, Hao Huang, Eng Siong Chng
Experimental results on an 8-accent English speech recognition show both methods can yield WERs close to the conventional ASR systems that completely ignore the accent, as well as desired AR accuracy.
no code implementations • 21 Oct 2020 • Hao Huang, Lingjing Wang, Xiang Li, Yi Fang
In this paper, we propose a novel meta-learning based 3D point signature model, named 3Dmetapointsignature (MEPS) network, that is capable of learning robust point signatures in 3D shapes.
no code implementations • COLING 2020 • Hao Huang, Guodong Long, Tao Shen, Jing Jiang, Chengqi Zhang
Many graph embedding approaches have been proposed for knowledge graph completion via link prediction.
no code implementations • 13 Aug 2020 • Hao Huang, Jianchun Chen, Xiang Li, Lingjing Wang, Yi Fang
Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching.
no code implementations • 19 May 2020 • Wenjie Li, Benlai Tang, Xiang Yin, Yushi Zhao, Wei Li, Kang Wang, Hao Huang, Yuxuan Wang, Zejun Ma
Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre.
no code implementations • 18 May 2020 • Tingzhi Mao, Yerbolat Khassanov, Van Tung Pham, Hai-Hua Xu, Hao Huang, Eng Siong Chng
In this paper, we present a series of complementary approaches to improve the recognition of underrepresented named entities (NE) in hybrid ASR systems without compromising overall word error rate performance.
2 code implementations • 30 Apr 2020 • Risheng Liu, Zi Li, Xin Fan, Chenying Zhao, Hao Huang, Zhongxuan Luo
We design a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation in order to integrate advantages and avoid limitations of these two categories of approaches.
no code implementations • 3 Dec 2019 • Fei Huang, Hao Huang
However, given all the historical transaction records, it is challenging to predict the sale price of the remaining seats at any future timestamp, not only because that the sale price is relevant to a lot of features (seat locations, date-to-event of the transaction, event date, team performance, etc.
no code implementations • 20 Jul 2019 • Hao Huang, Shinjae Yoo, and Yunwen Xu
Machine failure analysis and detection is critical to today’s industrial society.
no code implementations • 13 Dec 2018 • Hao Huang, Luowei Zhou, Wei zhang, Jason J. Corso, Chenliang Xu
Video action recognition, a critical problem in video understanding, has been gaining increasing attention.
no code implementations • 13 May 2017 • Shuchu Han, Hao Huang, Hong Qin
The redundant features existing in high dimensional datasets always affect the performance of learning and mining algorithms.