no code implementations • Findings (ACL) 2022 • Yu Xia, Quan Wang, Yajuan Lyu, Yong Zhu, Wenhao Wu, Sujian Li, Dai Dai
However, the existing method depends on the relevance between tasks and is prone to inter-type confusion. In this paper, we propose a novel two-stage framework Learn-and-Review (L&R) for continual NER under the type-incremental setting to alleviate the above issues. Specifically, for the learning stage, we distill the old knowledge from teacher to a student on the current dataset.
no code implementations • NAACL (BioNLP) 2021 • Songtai Dai, Quan Wang, Yajuan Lyu, Yong Zhu
This paper presents our winning system at the Radiology Report Summarization track of the MEDIQA 2021 shared task.
no code implementations • ECCV 2020 • Yating Wang, Quan Wang, Feng Xu
A complete 3D face reconstruction requires to explicitly model the eyeglasses on the face, which is less investigated in the literature.
no code implementations • 8 Apr 2022 • Shaojin Ding, Rajeev Rikhye, Qiao Liang, Yanzhang He, Quan Wang, Arun Narayanan, Tom O'Malley, Ian McGraw
Personalization of on-device speech recognition (ASR) has seen explosive growth in recent years, largely due to the increasing popularity of personal assistant features on mobile devices and smart home speakers.
no code implementations • 25 Mar 2022 • Zhenya Zang, Dong Xiao, Quan Wang, Zinuo Li, Wujun Xie, Yu Chen, David Day Uei Li
As there is no back-propagation process for ELM during the training phase, the training speed is much higher than existing neural network approaches.
1 code implementation • 24 Mar 2022 • Li SiYao, Weijiang Yu, Tianpei Gu, Chunze Lin, Quan Wang, Chen Qian, Chen Change Loy, Ziwei Liu
With the learned choreographic memory, dance generation is realized on the quantized units that meet high choreography standards, such that the generated dancing sequences are confined within the spatial constraints.
1 code implementation • 10 Mar 2022 • Jason Pelecanos, Quan Wang, Yiling Huang, Ignacio Lopez Moreno
This paper presents a novel study of parameter-free attentive scoring for speaker verification.
no code implementations • 24 Feb 2022 • Rajeev Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ian McGraw
However, one limitation of VoiceFilter-Lite, and other speaker-conditioned speech models in general, is that these models are usually limited to a single target speaker.
1 code implementation • 24 Feb 2022 • Quan Wang, Yang Yu, Jason Pelecanos, Yiling Huang, Ignacio Lopez Moreno
In this paper, we introduce a novel language identification system based on conformer layers.
1 code implementation • 11 Jan 2022 • Ye Jia, Michelle Tadmor Ramanovich, Quan Wang, Heiga Zen
In addition, CVSS provides normalized translation text which matches the pronunciation in the translation speech.
no code implementations • 18 Nov 2021 • Tom O'Malley, Arun Narayanan, Quan Wang, Alex Park, James Walker, Nathan Howard
Compared to the noisy baseline, the joint model reduces the word error rate in low signal-to-noise ratio conditions by at least 71% on our echo cancellation dataset, 10% on our noisy dataset, and 26% on our multi-speaker dataset.
no code implementations • 30 Oct 2021 • Arun Narayanan, Chung-Cheng Chiu, Tom O'Malley, Quan Wang, Yanzhang He
This work introduces \emph{cross-attention conformer}, an attention-based architecture for context modeling in speech enhancement.
1 code implementation • 14 Oct 2021 • Quan Wang, Songtai Dai, Benfeng Xu, Yajuan Lyu, Yong Zhu, Hua Wu, Haifeng Wang
In this work we introduce eHealth, a Chinese biomedical PLM built from scratch with a new pre-training framework.
1 code implementation • 23 Sep 2021 • Wei Xia, Han Lu, Quan Wang, Anshuman Tripathi, Yiling Huang, Ignacio Lopez Moreno, Hasim Sak
In this paper, we present a novel speaker diarization system for streaming on-device applications.
1 code implementation • 11 Aug 2021 • Beibin Li, Nicholas Nuechterlein, Erin Barney, Claire Foster, Minah Kim, Monique Mahony, Adham Atyabi, Li Feng, Quan Wang, Pamela Ventola, Linda Shapiro, Frederick Shic
Identifying oculomotor behaviors relevant for eye-tracking applications is a critical but often challenging task.
no code implementations • 2 Jul 2021 • Rajeev Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ian McGraw
In this paper, we propose a solution to allow speaker conditioned speech models, such as VoiceFilter-Lite, to support an arbitrary number of enrolled users in a single pass.
Automatic Speech Recognition
Text-Independent Speaker Verification
no code implementations • Findings (ACL) 2021 • Quan Wang, Haifeng Wang, Yajuan Lyu, Yong Zhu
The key to our approach is to represent the n-ary structure of a fact as a small heterogeneous graph, and model this graph with edge-biased fully-connected attention.
no code implementations • CVPR 2021 • Jingtan Piao, Keqiang Sun, KwanYee Lin, Quan Wang, Hongsheng Li
Since the GAR learns to model the complicated real-world image, instead of relying on the simplified graphics rules, it is capable of producing realistic images, which essentially inhibits the domain-shift noise in training and optimization.
no code implementations • 28 Apr 2021 • Rajeev Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ding Zhao, Yiteng, Huang, Arun Narayanan, Ian McGraw
In this paper, we introduce a streaming keyphrase detection system that can be easily customized to accurately detect any phrase composed of words from a large vocabulary.
no code implementations • 5 Apr 2021 • Roza Chojnacka, Jason Pelecanos, Quan Wang, Ignacio Lopez Moreno
To the best of our knowledge, this is the first study of speaker verification systems at the scale of 46 languages.
no code implementations • 5 Apr 2021 • Jason Pelecanos, Quan Wang, Ignacio Lopez Moreno
In this work we propose scoring these representations in a way that can capture uncertainty, enroll/test asymmetry and additional non-linear information.
2 code implementations • 20 Feb 2021 • Benfeng Xu, Quan Wang, Yajuan Lyu, Yong Zhu, Zhendong Mao
Our experiments demonstrate the usefulness of the proposed entity structure and the effectiveness of SSAN.
Ranked #2 on
Relation Extraction
on DocRED
no code implementations • 24 Nov 2020 • Yiling Huang, Yutian Chen, Jason Pelecanos, Quan Wang
In recent years, Text-To-Speech (TTS) has been used as a data augmentation technique for speech recognition to help complement inadequacies in the training data.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Fayuan Li, Weihua Peng, Yuguang Chen, Quan Wang, Lu Pan, Yajuan Lyu, Yong Zhu
Most traditional approaches formulate this task as classification problems, with event types or argument roles taken as golden labels.
1 code implementation • 9 Sep 2020 • Quan Wang, Ignacio Lopez Moreno, Mert Saglam, Kevin Wilson, Alan Chiao, Renjie Liu, Yanzhang He, Wei Li, Jason Pelecanos, Marily Nika, Alexander Gruenstein
We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system.
no code implementations • 13 Aug 2020 • Shaojin Ding, Ye Jia, Ke Hu, Quan Wang
In this paper, we propose Textual Echo Cancellation (TEC) - a framework for cancelling the text-to-speech (TTS) playback echo from overlapping speech recordings.
no code implementations • 23 Jul 2020 • Quan Wang, Ignacio Lopez Moreno
This paper discusses one of the most challenging practical engineering problems in speaker recognition systems - the version control of models and user profiles.
no code implementations • 12 Jul 2020 • Krushi Patel, Kaidong Li, Ke Tao, Quan Wang, Ajay Bansal, Amit Rastogi, Guanghui Wang
In this work, we compare the performance of the state-of-the-art general object classification models for polyp classification.
no code implementations • ACL 2020 • Benfeng Xu, Licheng Zhang, Zhendong Mao, Quan Wang, Hongtao Xie, Yongdong Zhang
With the great success of pre-trained language models, the pretrain-finetune paradigm now becomes the undoubtedly dominant solution for natural language understanding (NLU) tasks.
no code implementations • 21 Jun 2020 • Beier Zhu, Chunze Lin, Quan Wang, Renjie Liao, Chen Qian
In this paper, we propose a fast and accurate coordinate regression method for face alignment.
1 code implementation • 27 May 2020 • Yaming Yang, Ziyu Guan, Jian-Xin Li, Wei Zhao, Jiangtao Cui, Quan Wang
However, regarding Heterogeneous Information Network (HIN), existing HIN-oriented GCN methods still suffer from two deficiencies: (1) they cannot flexibly explore all possible meta-paths and extract the most useful ones for a target object, which hinders both effectiveness and interpretability; (2) they often need to generate intermediate meta-path based dense graphs, which leads to high computational complexity.
2 code implementations • 6 Nov 2019 • Quan Wang, Pingping Huang, Haifeng Wang, Songtai Dai, Wenbin Jiang, Jing Liu, Yajuan Lyu, Yong Zhu, Hua Wu
This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings.
no code implementations • 5 Nov 2019 • Xin Wang, Junichi Yamagishi, Massimiliano Todisco, Hector Delgado, Andreas Nautsch, Nicholas Evans, Md Sahidullah, Ville Vestman, Tomi Kinnunen, Kong Aik Lee, Lauri Juvela, Paavo Alku, Yu-Huai Peng, Hsin-Te Hwang, Yu Tsao, Hsin-Min Wang, Sebastien Le Maguer, Markus Becker, Fergus Henderson, Rob Clark, Yu Zhang, Quan Wang, Ye Jia, Kai Onuma, Koji Mushika, Takashi Kaneda, Yuan Jiang, Li-Juan Liu, Yi-Chiao Wu, Wen-Chin Huang, Tomoki Toda, Kou Tanaka, Hirokazu Kameoka, Ingmar Steiner, Driss Matrouf, Jean-Francois Bonastre, Avashna Govender, Srikanth Ronanki, Jing-Xuan Zhang, Zhen-Hua Ling
Spoofing attacks within a logical access (LA) scenario are generated with the latest speech synthesis and voice conversion technologies, including state-of-the-art neural acoustic and waveform model techniques.
no code implementations • WS 2019 • Hongyu Li, Xiyuan Zhang, Yibing Liu, Yiming Zhang, Quan Wang, Xiangyang Zhou, Jing Liu, Hua Wu, Haifeng Wang
In this paper, we introduce a simple system Baidu submitted for MRQA (Machine Reading for Question Answering) 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models.
1 code implementation • ICCV 2019 • Keqiang Sun, Wayne Wu, Tinghao Liu, Shuo Yang, Quan Wang, Qiang Zhou, Zuochang Ye, Chen Qian
A structure predictor is proposed to predict the missing face structural information temporally, which serves as a geometry prior.
no code implementations • ICCV 2019 • Shengju Qian, Kwan-Yee Lin, Wayne Wu, Yangxiaokang Liu, Quan Wang, Fumin Shen, Chen Qian, Ran He
Recent studies have shown remarkable success in face manipulation task with the advance of GANs and VAEs paradigms, but the outputs are sometimes limited to low-resolution and lack of diversity.
2 code implementations • 12 Aug 2019 • Shaojin Ding, Quan Wang, Shuo-Yiin Chang, Li Wan, Ignacio Lopez Moreno
In this paper, we propose "personal VAD", a system to detect the voice activity of a target speaker at the frame level.
1 code implementation • ACL 2019 • An Yang, Quan Wang, Jing Liu, Kai Liu, Yajuan Lyu, Hua Wu, Qiaoqiao She, Sujian Li
In this work, we investigate the potential of leveraging external knowledge bases (KBs) to further improve BERT for MRC.
no code implementations • NAACL 2019 • Xiaotian Jiang, Quan Wang, Bin Wang
We consider the problem of learning distributed representations for entities and relations of multi-relational data so as to predict missing links therein.
Ranked #10 on
Link Prediction
on WN18
1 code implementation • 29 Nov 2018 • Li Wan, Prashant Sridhar, Yang Yu, Quan Wang, Ignacio Lopez Moreno
In many scenarios of a language identification task, the user will specify a small set of languages which he/she can speak instead of a large set of all possible languages.
5 code implementations • 11 Oct 2018 • Quan Wang, Hannah Muckenhirn, Kevin Wilson, Prashant Sridhar, Zelin Wu, John Hershey, Rif A. Saurous, Ron J. Weiss, Ye Jia, Ignacio Lopez Moreno
In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker.
1 code implementation • 10 Oct 2018 • Aonan Zhang, Quan Wang, Zhenyao Zhu, John Paisley, Chong Wang
In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN).
Ranked #1 on
Speaker Diarization
on Hub5'00 CallHome
no code implementations • ICLR 2019 • Yutian Chen, Yannis Assael, Brendan Shillingford, David Budden, Scott Reed, Heiga Zen, Quan Wang, Luis C. Cobo, Andrew Trask, Ben Laurie, Caglar Gulcehre, Aäron van den Oord, Oriol Vinyals, Nando de Freitas
Instead, the aim is to produce a network that requires few data at deployment time to rapidly adapt to new speakers.
no code implementations • 4 Sep 2018 • Xi Mo, Ke Tao, Quan Wang, Guanghui Wang
Polyp has long been considered as one of the major etiologies to colorectal cancer which is a fatal disease around the world, thus early detection and recognition of polyps plays a crucial role in clinical routines.
11 code implementations • NeurIPS 2018 • Ye Jia, Yu Zhang, Ron J. Weiss, Quan Wang, Jonathan Shen, Fei Ren, Zhifeng Chen, Patrick Nguyen, Ruoming Pang, Ignacio Lopez Moreno, Yonghui Wu
Clone a voice in 5 seconds to generate arbitrary speech in real-time
2 code implementations • CVPR 2018 • Wayne Wu, Chen Qian, Shuo Yang, Quan Wang, Yici Cai, Qiang Zhou
By utilising boundary information of 300-W dataset, our method achieves 3. 92% mean error with 0. 39% failure rate on COFW dataset, and 1. 25% mean error on AFLW-Full dataset.
Ranked #2 on
Face Alignment
on AFLW-19
(using extra training data)
1 code implementation • ACL 2018 • Boyang Ding, Quan Wang, Bin Wang, Li Guo
We examine non-negativity constraints on entity representations and approximate entailment constraints on relation representations.
1 code implementation • 30 Jan 2018 • Philip Andrew Mansfield, Quan Wang, Carlton Downey, Li Wan, Ignacio Lopez Moreno
We present a novel algorithm, called Links, designed to perform online clustering on unit vectors in a high-dimensional Euclidean space.
1 code implementation • 1 Dec 2017 • W. Bastiaan Kleijn, Felicia S. C. Lim, Alejandro Luebs, Jan Skoglund, Florian Stimberg, Quan Wang, Thomas C. Walters
Traditional parametric coding of speech facilitates low rate but provides poor reconstruction quality because of the inadequacy of the model used.
1 code implementation • 30 Nov 2017 • Shu Guo, Quan Wang, Lihong Wang, Bin Wang, Li Guo
In this paper, we propose Rule-Guided Embedding (RUGE), a novel paradigm of KG embedding with iterative guidance from soft rules.
Ranked #2 on
Link Prediction
on YAGO37
28 code implementations • 28 Oct 2017 • Li Wan, Quan Wang, Alan Papir, Ignacio Lopez Moreno
In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function.
Ranked #1 on
Speaker Verification
on CALLHOME
4 code implementations • 28 Oct 2017 • Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio Lopez Moreno
For many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications.
2 code implementations • 28 Oct 2017 • F A Rezaur Rahman Chowdhury, Quan Wang, Ignacio Lopez Moreno, Li Wan
Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire length of an input sequence.
no code implementations • COLING 2016 • Xiaotian Jiang, Quan Wang, Peng Li, Bin Wang
In this paper, we propose a multi-instance multi-label convolutional neural network for distantly supervised RE.
1 code implementation • 2014 22nd International Conference on Pattern Recognition 2014 • Quan Wang, Xin Shen, Meng Wang, Kim L. Boyer
In this paper, we present a simple and efficient way to add supervised information into Fisher vectors, which has become a popular image representation method for image classification and retrieval purposes in recent years.
1 code implementation • 11 Jul 2013 • Quan Wang, Dijia Wu, Le Lu, Meizhu Liu, Kim L. Boyer, Shaohua Kevin Zhou
The automatic segmentation of human knee cartilage from 3D MR images is a useful yet challenging task due to the thin sheet structure of the cartilage with diffuse boundaries and inhomogeneous intensities.
1 code implementation • 14 Jun 2013 • Quan Wang, Kim L. Boyer
The aspects of the images that are captured by the learned features, which we call MDS features, completely depend on what kind of image distance measurement is employed.
1 code implementation • 18 Dec 2012 • Quan Wang
In this project, we first study the Gaussian-based hidden Markov random field (HMRF) model and its expectation-maximization (EM) algorithm.
1 code implementation • journal 2012 • Quan Wang, Kim L. Boyer
Similar to active shape models and active contours, a force field is used in our approach.
2 code implementations • 15 Jul 2012 • Quan Wang
Principal component analysis (PCA) is a popular tool for linear dimensionality reduction and feature extraction.
1 code implementation • 15 Jul 2012 • Quan Wang
In this project, we study the hidden Markov random field (HMRF) model and its expectation-maximization (EM) algorithm.
1 code implementation • 13 Jul 2012 • Quan Wang, Yan Ou, A. Agung Julius, Kim L. Boyer, Min Jun Kim
Matching cells over time has long been the most difficult step in cell tracking.