Search Results for author: Quan Wang

Found 69 papers, 34 papers with code

Learn and Review: Enhancing Continual Named Entity Recognition via Reviewing Synthetic Samples

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.

Continual Learning Named Entity Recognition +1

Eyeglasses 3D shape reconstruction from a single face image

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.

3D Face Reconstruction 3D Reconstruction +2

Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition

no code implementations8 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.

Action Detection Activity Detection +1

Fast fluorescence lifetime imaging analysis via extreme learning machine

no code implementations25 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.

Edge-computing

Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory

1 code implementation24 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.

Parameter-Free Attentive Scoring for Speaker Verification

1 code implementation10 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.

Speaker Verification

Closing the Gap between Single-User and Multi-User VoiceFilter-Lite

no code implementations24 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.

Speaker Verification Speech Recognition

A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation

no code implementations18 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.

Acoustic echo cancellation Automatic Speech Recognition +2

Cross-attention conformer for context modeling in speech enhancement for ASR

no code implementations30 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.

Automatic Speech Recognition Speech Enhancement

Building Chinese Biomedical Language Models via Multi-Level Text Discrimination

1 code implementation14 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.

Domain Adaptation

Multi-user VoiceFilter-Lite via Attentive Speaker Embedding

no code implementations2 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

Link Prediction on N-ary Relational Facts: A Graph-based Approach

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.

Knowledge Graphs Link Prediction

Inverting Generative Adversarial Renderer for Face Reconstruction

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.

Face Reconstruction

Personalized Keyphrase Detection using Speaker and Environment Information

no code implementations28 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.

Automatic Speech Recognition Speaker Separation +1

Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognition

no code implementations5 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.

Speaker Recognition

Synth2Aug: Cross-domain speaker recognition with TTS synthesized speech

no code implementations24 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.

Data Augmentation Speaker Recognition +1

VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition

1 code implementation9 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.

Speech Recognition

Textual Echo Cancellation

no code implementations13 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.

Acoustic echo cancellation Speech Recognition

Version Control of Speaker Recognition Systems

no code implementations23 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.

Speaker Recognition

A Comparative Study on Polyp Classification using Convolutional Neural Networks

no code implementations12 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.

Classification General Classification

Curriculum Learning for Natural Language Understanding

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.

Natural Language Understanding

Fast and Accurate: Structure Coherence Component for Face Alignment

no code implementations21 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.

Face Alignment

Interpretable and Efficient Heterogeneous Graph Convolutional Network

1 code implementation27 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.

CoKE: Contextualized Knowledge Graph Embedding

2 code implementations6 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.

Knowledge Graph Embedding Link Prediction

D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension

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.

Machine Reading Comprehension Multi-Task Learning +1

Make a Face: Towards Arbitrary High Fidelity Face Manipulation

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.

Disentanglement

Personal VAD: Speaker-Conditioned Voice Activity Detection

2 code implementations12 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.

Action Detection Activity Detection +4

Adaptive Convolution for Multi-Relational Learning

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.

Link Prediction Relational Reasoning

Tuplemax Loss for Language Identification

1 code implementation29 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.

Language Identification

VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking

5 code implementations11 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.

Speaker Recognition Speaker Separation +2

Fully Supervised Speaker Diarization

1 code implementation10 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).

Speaker Diarization

An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN

no code implementations4 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.

Look at Boundary: A Boundary-Aware Face Alignment Algorithm

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)

Face Alignment Facial Landmark Detection

Improving Knowledge Graph Embedding Using Simple Constraints

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.

Knowledge Graph Embedding Knowledge Graphs

Links: A High-Dimensional Online Clustering Method

1 code implementation30 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.

Online Clustering

Wavenet based low rate speech coding

1 code implementation1 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.

Bandwidth Extension

Knowledge Graph Embedding with Iterative Guidance from Soft Rules

1 code implementation30 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.

Knowledge Graph Embedding Knowledge Graphs +1

Generalized End-to-End Loss for Speaker Verification

28 code implementations28 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.

Domain Adaptation Speaker Verification

Speaker Diarization with LSTM

4 code implementations28 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.

Speaker Diarization Speaker Verification

Attention-Based Models for Text-Dependent Speaker Verification

2 code implementations28 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.

14 Image Captioning +5

Label Consistent Fisher Vectors for Supervised Feature Aggregation

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.

Classification General Classification +1

Semantic Context Forests for Learning-Based Knee Cartilage Segmentation in 3D MR Images

1 code implementation11 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.

3D Medical Imaging Segmentation

Feature Learning by Multidimensional Scaling and its Applications in Object Recognition

1 code implementation14 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.

Object Recognition

GMM-Based Hidden Markov Random Field for Color Image and 3D Volume Segmentation

1 code implementation18 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.

Semantic Segmentation

Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models

2 code implementations15 Jul 2012 Quan Wang

Principal component analysis (PCA) is a popular tool for linear dimensionality reduction and feature extraction.

Dimensionality Reduction Face Recognition +1

HMRF-EM-image: Implementation of the Hidden Markov Random Field Model and its Expectation-Maximization Algorithm

1 code implementation15 Jul 2012 Quan Wang

In this project, we study the hidden Markov random field (HMRF) model and its expectation-maximization (EM) algorithm.

Semantic Segmentation

Tracking Tetrahymena Pyriformis Cells using Decision Trees

1 code implementation13 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.

Frame

Cannot find the paper you are looking for? You can Submit a new open access paper.