Search Results for author:
Found 278 papers, 62 papers with code
Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages
Recent emergence of multilingual pre-training language model (mPLM) has enabled breakthroughs on various downstream cross-lingual transfer (CLT) tasks.
Learning to See in the Dark with Events
A detail enhancing branch is proposed to reconstruct day light-specific features from the domain-invariant representations in a residual manner, regularized by a ranking loss.
Dynamic Feature Alignment for Semi-supervised Domain Adaptation
Most research on domain adaptation has focused on the purely unsupervised setting, where no labeled examples in the target domain are available.
SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-training natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning.
Region Semantically Aligned Network for Zero-Shot Learning
Zero-shot learning (ZSL) aims to recognize unseen classes based on the knowledge of seen classes.
Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments
Semantic role labeling is a fundamental yet challenging task in the NLP community.
Ranked #1 on
Semantic Role Labeling
on CoNLL 2005
Multi-View Self-Attention Based Transformer for Speaker Recognition
In this work, we propose a novel multi-view self-attention mechanism and present an empirical study of different Transformer variants with or without the proposed attention mechanism for speaker recognition.
Universal Paralinguistic Speech Representations Using Self-Supervised Conformers
Many speech applications require understanding aspects beyond the words being spoken, such as recognizing emotion, detecting whether the speaker is wearing a mask, or distinguishing real from synthetic speech.
Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition
As end-to-end automatic speech recognition (ASR) models reach promising performance, various downstream tasks rely on good confidence estimators for these systems.
automatic-speech-recognition
End-To-End Speech Recognition
+2
Learning Material Parameters and Hydrodynamics of Soft Robotic Fish via Differentiable Simulation
We address this gap with our differentiable simulation tool by learning the material parameters and hydrodynamics of our robots.
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio.
Comparison of Object Detection Algorithms Using Video and Thermal Images Collected from a UAS Platform: An Application of Drones in Traffic Management
The results show that a background subtraction-based method can achieve good detection performance on RGB images (F1 scores around 0. 9 for most cases), and a more varied performance is seen on thermal images with different azimuth angles.
A Simple Self-calibration Method for The Internal Time Synchronization of MEMS LiDAR
This paper proposes a simple self-calibration method for the internal time synchronization of MEMS(Micro-electromechanical systems) LiDAR during research and development.
Multi-Task Learning in Natural Language Processing: An Overview
Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP).
Generating Active Explicable Plans in Human-Robot Teaming
In our experimental evaluation, we verify that our approach generates more efficient explicable plans while successfully capturing the dynamic belief change of the human teammate.
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification
Specifically, we first retrieve logic-level program-like evidence from the given table and statement as supplementary evidence for the table.
Domain Adaptation by Maximizing Population Correlation with Neural Architecture Search
Base on the PC function, we propose a new method called Domain Adaptation by Maximizing Population Correlation (DAMPC) to learn a domain-invariant feature representation for DA.
Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training
We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base.
Injecting Text in Self-Supervised Speech Pretraining
The proposed method, tts4pretrain complements the power of contrastive learning in self-supervision with linguistic/lexical representations derived from synthesized speech, effectively learning from untranscribed speech and unspoken text.
Attention-based Neural Load Forecasting: A Dynamic Feature Selection Approach
Then, a decoder with hierarchical temporal attention enables a similar day selection, which re-evaluates the importance of historical information at each time step.
Online Dictionary Learning Based Fault and Cyber Attack Detection for Power Systems
This paper deals with the event and intrusion detection problem by leveraging a stream data mining classifier (Hoeffding adaptive tree) with semi-supervised learning techniques to distinguish cyber-attacks from regular system perturbations accurately.
Mitigating Greenhouse Gas Emissions Through Generative Adversarial Networks Based Wildfire Prediction
Over the past decade, the number of wildfire has increased significantly around the world, especially in the State of California.
Reinforcement Learning for Robot Navigation with Adaptive ExecutionDuration (AED) in a Semi-Markov Model
Specifically, we formulate the navigation task as a Semi-Markov Decision Process (SMDP) problem to handle adaptive execution duration.
W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training
In particular, when compared to published models such as conformer-based wav2vec~2. 0 and HuBERT, our model shows~5\% to~10\% relative WER reduction on the test-clean and test-other subsets.
Personalized Image Semantic Segmentation
In this paper, we address the problem of personalized image segmentation.
Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting
As cameras are increasingly deployed in new application domains such as autonomous driving, performing 3D object detection on monocular images becomes an important task for visual scene understanding.
Multi-Modal 3D Object Detection in Autonomous Driving: a Survey
In this survey, we first introduce the background of popular sensors for autonomous cars, including their common data representations as well as object detection networks developed for each type of sensor data.
Sparse Multi-Path Corrections in Fringe Projection Profilometry
Three-dimensional scanning by means of structured light illumination is an active imaging technique involving projecting and capturing a series of striped patterns and then using the observed warping of stripes to reconstruct the target object's surface through triangulating each pixel in the camera to a unique projector coordinate corresponding to a particular feature in the projected patterns.
Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection
Cross-domain weakly supervised object detection aims to adapt object-level knowledge from a fully labeled source domain dataset (i. e. with object bounding boxes) to train object detectors for target domains that are weakly labeled (i. e. with image-level tags).
WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
The model takes an input phoneme sequence, and through an iterative refinement process, generates an audio waveform.
FedNILM: Applying Federated Learning to NILM Applications at the Edge
Non-intrusive load monitoring (NILM) helps disaggregate the household's main electricity consumption to energy usages of individual appliances, thus greatly cutting down the cost in fine-grained household load monitoring.
Rethinking Training from Scratch for Object Detection
The ImageNet pre-training initialization is the de-facto standard for object detection.
More Behind Your Electricity Bill: a Dual-DNN Approach to Non-Intrusive Load Monitoring
Non-intrusive load monitoring (NILM) is a well-known single-channel blind source separation problem that aims to decompose the household energy consumption into itemised energy usage of individual appliances.
Large-Signal Grid-Synchronization Stability Analysis of PLL-based VSCs Using Lyapunov's Direct Method
Grid-synchronization stability (GSS) is an emerging stability issue of grid-tied voltage source converters (VSCs), which can be provoked by severe grid voltage sags.
Scaling End-to-End Models for Large-Scale Multilingual ASR
Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data.
Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction
Confidence scores are very useful for downstream applications of automatic speech recognition (ASR) systems.
automatic-speech-recognition
End-To-End Speech Recognition
+2
Deep Latent Emotion Network for Multi-Task Learning
DLEN is deployed on a real-world multi-task feed recommendation scenario of Tencent QQ-Small-World with a dataset containing over a billion samples, and it exhibits a significant performance advantage over the SOTA MTL model in offline evaluation, together with a considerable increase by 3. 02% in view-count and 2. 63% in user stay-time in production.
CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework
Asynchronous FL has a natural advantage in mitigating the straggler effect, but there are threats of model quality degradation and server crash.
FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems
In our framework, the server evaluates devices' value of training based on their training loss.
Pushing the Limits of Non-Autoregressive Speech Recognition
We combine recent advancements in end-to-end speech recognition to non-autoregressive automatic speech recognition.
automatic-speech-recognition
End-To-End Speech Recognition
+2
Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models
To attack RNN-T, we find prepending perturbation is more effective than the additive perturbation, and can mislead the models to predict the same short target on utterances of arbitrary length.
automatic-speech-recognition
End-To-End Speech Recognition
+1
SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
We present SpeechStew, a speech recognition model that is trained on a combination of various publicly available speech recognition datasets: AMI, Broadcast News, Common Voice, LibriSpeech, Switchboard/Fisher, Tedlium, and Wall Street Journal.
Ranked #1 on
Speech Recognition
on Common Voice
Using Simulation to Aid the Design and Optimization of Intelligent User Interfaces for Quality Assurance Processes in Machine Learning
Because QA4ML users have to view a non-trivial amount of data and perform many input actions to correct errors made by the ML model, an optimally-designed user interface (UI) can reduce the cost of interactions significantly.
PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS
This paper introduces PnG BERT, a new encoder model for neural TTS.
On the limits of algorithmic prediction across the globe
We tested how well predictive models of human behavior trained in a developed country generalize to people in less developed countries by modeling global variation in 200 predictors of academic achievement on nationally representative student data for 65 countries.
Residual Energy-Based Models for End-to-End Speech Recognition
End-to-end models with auto-regressive decoders have shown impressive results for automatic speech recognition (ASR).
automatic-speech-recognition
End-To-End Speech Recognition
+2
Learning Word-Level Confidence For Subword End-to-End ASR
We study the problem of word-level confidence estimation in subword-based end-to-end (E2E) models for automatic speech recognition (ASR).
automatic-speech-recognition
End-To-End Speech Recognition
+3
Deciphering Star Cluster Evolution by Shape Morphology
A significant negative correlation between the overall ellipticities and masses is also detected for the sample clusters with log(age/year) $\geq$ 8, suggesting that the overall shapes of the clusters are possibly influenced by the number of members and masses, in addition to the external forces and the surrounding environment.
Astrophysics of Galaxies Solar and Stellar Astrophysics
Self-supervised Low Light Image Enhancement and Denoising
Both of the networks can be trained with low light images only, which is achieved by a Maximum Entropy based Retinex (ME-Retinex) model and an assumption that noises are independently distributed.
Fronthaul Compression and Passive Beamforming Design for Intelligent Reflecting Surface-aided Cloud Radio Access Networks
This letter studies a cloud radio access network (C-RAN) with multiple intelligent reflecting surfaces (IRS) deployed between users and remote radio heads (RRH).
Reinforcement Learning for Beam Pattern Design in Millimeter Wave and Massive MIMO Systems
Employing large antenna arrays is a key characteristic of millimeter wave (mmWave) and terahertz communication systems.
Echo State Speech Recognition
We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained.
MATCH: Metadata-Aware Text Classification in A Large Hierarchy
Multi-label text classification refers to the problem of assigning each given document its most relevant labels from the label set.
Multi-Objective Meta Learning
Empirically, we show the effectiveness of the proposed MOML framework in several meta learning problems, including few-shot learning, neural architecture search, domain adaptation, and multi-task learning.
Phase discontinuities induced scintillation enhancement: coherent vortex beams propagating through weak oceanic turbulence
Under the impact of an infinitely extended edge phase dislocation, optical vortices (screw phase dislocations) induce scintillation enhancement.
Optics
Joint Transmit Precoding and Reflect Beamforming Design for IRS-Assisted MIMO Cognitive Radio Systems
Cognitive radio (CR) is an effective solution to improve the spectral efficiency (SE) of wireless communications by allowing the secondary users (SUs) to share spectrum with primary users (PUs).
Information Theory Signal Processing Information Theory
Photoproduction $γp \to K^+Λ(1520)$ in an effective Lagrangian approach
In addition to the $t$-channel $K$ and $K^\ast$ exchanges, the $u$-channel $\Lambda$ exchange, the $s$-channel nucleon exchange, and the interaction current, a minimal number of nucleon resonances in the $s$ channel are introduced in constructing the reaction amplitudes to describe the data.
High Energy Physics - Phenomenology Nuclear Theory
Generative Adversarial U-Net for Domain-free Medical Image Augmentation
The shortage of annotated medical images is one of the biggest challenges in the field of medical image computing.
Model-based cellular kinetic analysis of SARS-CoV-2 infection: different immune response modes and treatment strategies
Integrating theoretical results with clinical COVID-19 patients' data, we classified the COVID-19 development processes into three typical modes of immune responses, correlated with the clinical classification of mild & moderate, severe and critical patients.
Training Weakly Supervised Video Frame Interpolation With Events
Though trained on low frame-rate videos, our framework outperforms existing models trained with full high frame-rate videos (and events) on both GoPro dataset and a new real event-based dataset.
FOC OSOD: Focus on Classification One-Shot Object Detection
This paper analyzes the serious false positive problem in OSOD and proposes a Focus on Classification One-Shot Object Detection (FOC OSOD) framework, which is improved in two important aspects: (1) classification cascade head with the fixed IoU threshold can enhance the robustness of classification by comparing multiple close regions; (2) classification region deformation on the query feature and the reference feature to obtain a more effective comparison region.
Multiple Structural Priors Guided Self Attention Network for Language Understanding
Self attention networks (SANs) have been widely utilized in recent NLP studies.
A Survey on Neural Network Interpretability
Along with the great success of deep neural networks, there is also growing concern about their black-box nature.
On Convergence of Gradient Expected Sarsa($λ$)
We study the convergence of $\mathtt{Expected~Sarsa}(\lambda)$ with linear function approximation.
Improving EEG Decoding via Clustering-based Multi-task Feature Learning
With the encoded label matrix, we devise a novel multi-task learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses.
Learn to Predict Vertical Track Irregularity with Extremely Imbalanced Data
Railway systems require regular manual maintenance, a large part of which is dedicated to inspecting track deformation.
Optical Wavelength Guided Self-Supervised Feature Learning For Galaxy Cluster Richness Estimate
We believe the proposed method will benefit astronomy and cosmology, where a large number of unlabeled multi-band images are available, but acquiring image labels is costly.
Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification
Table-based fact verification is expected to perform both linguistic reasoning and symbolic reasoning.
A robust and generalizable immune-relatedsignature for sepsis diagnostics
High-throughput sequencing can detect tens of thousands of genes in parallel, providing opportunities for improving the diagnostic accuracy of multiple diseases including sepsis, which is an aggressive inflammatory response to infection that can cause organ failure and death.
A Better and Faster End-to-End Model for Streaming ASR
To address this, we explore replacing the LSTM layers in the encoder of our E2E model with Conformer layers [4], which has shown good improvements for ASR.
Audio and Speech Processing Sound
Multi-Task Adversarial Attack
More specifically, MTA uses a generator for adversarial perturbations which consists of a shared encoder for all tasks and multiple task-specific decoders.
Effective, Efficient and Robust Neural Architecture Search
Although NAS methods can find network architectures with the state-of-the-art performance, the adversarial robustness and resource constraint are often ignored in NAS.
Domain Concretization from Examples: Addressing Missing Domain Knowledge via Robust Planning
This problem is more challenging than partial observability in the sense that the agent is unaware of certain knowledge, in contrast to it being partially observable: the difference between known unknowns and unknown unknowns.
Large-scale multilingual audio visual dubbing
The visual content is translated by synthesizing lip movements for the speaker to match the translated audio, creating a seamless audiovisual experience in the target language.
Fault Detection for Covered Conductors With High-Frequency Voltage Signals: From Local Patterns to Global Features
The detection and characterization of partial discharge (PD) are crucial for the insulation diagnosis of overhead lines with covered conductors.
Hierarchical Metadata-Aware Document Categorization under Weak Supervision
Our experiments demonstrate a consistent improvement of HiMeCat over competitive baselines and validate the contribution of our representation learning and data augmentation modules.
Unsupervised Learning of Disentangled Speech Content and Style Representation
We present an approach for unsupervised learning of speech representation disentangling contents and styles.
Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition
For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions.
automatic-speech-recognition
End-To-End Speech Recognition
+2
Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data
We propose a novel and effective learning method by leveraging a non-streaming ASR model as a teacher to generate transcripts on an arbitrarily large data set, which is then used to distill knowledge into streaming ASR models.
Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
We employ a combination of recent developments in semi-supervised learning for automatic speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabeled audio of the Libri-Light dataset.
Ranked #1 on
Speech Recognition
on LibriSpeech test-clean
(using extra training data)
Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling
This paper presents Non-Attentive Tacotron based on the Tacotron 2 text-to-speech model, replacing the attention mechanism with an explicit duration predictor.
Contrastive Cross-Modal Pre-Training: A General Strategy for Small Sample Medical Imaging
A key challenge in training neural networks for a given medical imaging task is often the difficulty of obtaining a sufficient number of manually labeled examples.
Cross-Modal Alignment with Mixture Experts Neural Network for Intral-City Retail Recommendation
At top of the MoE layer, we deploy a transformer layer for each task as task tower to learn task-specific information.
Boosting Retailer Revenue by Generated Optimized Combined Multiple Digital Marketing Campaigns
Secondly, based on the sub-modular optimization theory and the DMC pool by DMCNet, the generated combined multiple DMCs are ranked with respect to their revenue generation strength then the top three ranked campaigns are returned to the sellers' back-end management system, so that retailers can set combined multiple DMCs for their online shops just in one-shot.
Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification
Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain.
Oceanic non-Kolmogorov optical turbulence and spherical wave propagation
In particular, for natural water turbulence several models for the spatial power spectra have been developed based on the classic, Kolmogorov postulates.
Atmospheric and Oceanic Physics Optics
WaveGrad: Estimating Gradients for Waveform Generation
This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density.
An End-to-End Attack on Text-based CAPTCHAs Based on Cycle-Consistent Generative Adversarial Network
Firstly, we train CAPTCHA synthesizers based on the cycle-GAN to generate some fake samples.
Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks
The network takes low light images as input and the enhanced V channel as condition, then it can re-enhance the contrast and brightness of the low light image and at the same time reduce noise and color distortion.
Fast and Accurate Neural CRF Constituency Parsing
Estimating probability distribution is one of the core issues in the NLP field.
Ranked #1 on
Constituency Parsing
on CTB7
MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Prediction
Our study is based on UC Toutiao (a news feed service integrated with the UC Browser App, serving hundreds of millions of users daily), where the source domain is the news and the target domain is the ad.
Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
In reality, however, it is not uncommon to obtain samples from multiple heterogeneous domains.
COMET: Convolutional Dimension Interaction for Collaborative Filtering
In this paper, we propose a novel latent factor model called COMET (COnvolutional diMEnsion inTeraction), which simultaneously model the high-order interaction patterns among historical interactions and embedding dimensions.
A Study on Evaluation Standard for Automatic Crack Detection Regard the Random Fractal
In CovEval, a different matching process based on the idea of covering box matching is adopted for this issue.
Deep Image Clustering with Category-Style Representation
In this paper, we propose a novel deep image clustering framework to learn a category-style latent representation in which the category information is disentangled from image style and can be directly used as the cluster assignment.
Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding
Mining a set of meaningful topics organized into a hierarchy is intuitively appealing since topic correlations are ubiquitous in massive text corpora.
Ranked #1 on
Topic Models
on NYT
Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge
Deep learning-based methods have achieved state-of-the-art performance; however, one of major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners.
Allocation of Multi-Robot Tasks with Task Variants
We referred to this new problem as the multi-robot task allocation problem with task variants.
A Multi-spectral Dataset for Evaluating Motion Estimation Systems
The multi-spectral images, including both color and thermal images in full sensor resolution (640 x 480), are obtained from a standard and a long-wave infrared camera at 32Hz with hardware-synchronization.
Offline Handwritten Chinese Text Recognition with Convolutional Neural Networks
Deep learning based methods have been dominating the text recognition tasks in different and multilingual scenarios.
Neural Networks Based Beam Codebooks: Learning mmWave Massive MIMO Beams that Adapt to Deployment and Hardware
To overcome these limitations, this paper develops an efficient online machine learning framework that learns how to adapt the codebook beam patterns to the specific deployment, surrounding environment, user distribution, and hardware characteristics.
Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Images
Diagnosis from chest CT images is a promising direction.
Distant Transfer Learning via Deep Random Walk
Transfer learning, which is to improve the learning performance in the target domain by leveraging useful knowledge from the source domain, often requires that those two domains are very close, which limits its application scope.
M2Net: Multi-modal Multi-channel Network for Overall Survival Time Prediction of Brain Tumor Patients
Then, we use a modality-specific network to extract implicit and high-level features from different MR scans.
Attention: to Better Stand on the Shoulders of Giants
In the progress of science, the previously discovered knowledge principally inspires new scientific ideas, and citation is a reasonably good reflection of this cumulative nature of scientific research.
Improved Noisy Student Training for Automatic Speech Recognition
Noisy student training is an iterative self-training method that leverages augmentation to improve network performance.
Ranked #3 on
Speech Recognition
on LibriSpeech test-clean
(using extra training data)
Conformer: Convolution-augmented Transformer for Speech Recognition
Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs).
Ranked #7 on
Speech Recognition
on LibriSpeech test-other
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2. 1%/4. 6% without external language model (LM), 1. 9%/4. 1% with LM and 2. 9%/7. 0% with only 10M parameters on the clean/noisy LibriSpeech test sets.
Ranked #7 on
Speech Recognition
on LibriSpeech test-clean
automatic-speech-recognition
End-To-End Speech Recognition
+2
RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions
On a long-form YouTube test set, when the nonstreaming RNN-T model is trained with shorter segments of data, the proposed combination improves word error rate (WER) from 22. 3% to 14. 8%; when the streaming RNN-T model trained on short Search queries, the proposed techniques improve WER on the YouTube set from 67. 0% to 25. 3%.
Efficient Second-Order TreeCRF for Neural Dependency Parsing
Experiments and analysis on 27 datasets from 13 languages clearly show that techniques developed before the DL era, such as structural learning (global TreeCRF loss) and high-order modeling are still useful, and can further boost parsing performance over the state-of-the-art biaffine parser, especially for partially annotated training data.
Ranked #1 on
Dependency Parsing
on CoNLL-2009
Minimally Supervised Categorization of Text with Metadata
Then, based on the same generative process, we synthesize training samples to address the bottleneck of label scarcity.
A Large Scale Speech Sentiment Corpus
We present a multimodal corpus for sentiment analysis based on the existing Switchboard-1 Telephone Speech Corpus released by the Linguistic Data Consortium.
Partially-Typed NER Datasets Integration: Connecting Practice to Theory
While typical named entity recognition (NER) models require the training set to be annotated with all target types, each available datasets may only cover a part of them.
Learning an Adaptive Model for Extreme Low-light Raw Image Processing
Furthermore, those tests illustrate that the proposed method is able to adaptively control the global image brightness according to the content of the image scene.
Order Matters: Generating Progressive Explanations for Planning Tasks in Human-Robot Teaming
Given this sequential process, a formulation based on goal-based MDP for generating progressive explanations is presented.
Learning Event-Based Motion Deblurring
Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process.
Ranked #8 on
Deblurring
on GoPro
(using extra training data)
Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images
The novel coronavirus disease 2019 (COVID-19) has been spreading rapidly around the world and caused significant impact on the public health and economy.
Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
Since there has already been a broad body of HNE algorithms, as the first contribution of this work, we provide a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms.
A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i. e., word error rate (WER), and latency, i. e., the time the hypothesis is finalized after the user stops speaking.
CF2-Net: Coarse-to-Fine Fusion Convolutional Network for Breast Ultrasound Image Segmentation
Breast ultrasound (BUS) image segmentation plays a crucial role in a computer-aided diagnosis system, which is regarded as a useful tool to help increase the accuracy of breast cancer diagnosis.
Fisher Deep Domain Adaptation
Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance.
Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?
In the pre deep learning era, part-of-speech tags have been considered as indispensable ingredients for feature engineering in dependency parsing.
Unsupervised Domain Adaptation for Mammogram Image Classification: A Promising Tool for Model Generalization
Generalization is one of the key challenges in the clinical validation and application of deep learning models to medical images.
Defense-PointNet: Protecting PointNet Against Adversarial Attacks
Despite remarkable performance across a broad range of tasks, neural networks have been shown to be vulnerable to adversarial attacks.
2D Convolutional Neural Networks for 3D Digital Breast Tomosynthesis Classification
Automated methods for breast cancer detection have focused on 2D mammography and have largely ignored 3D digital breast tomosynthesis (DBT), which is frequently used in clinical practice.
Attention-guided Chained Context Aggregation for Semantic Segmentation
The way features propagate in Fully Convolutional Networks is of momentous importance to capture multi-scale contexts for obtaining precise segmentation masks.
Joint 2D-3D Breast Cancer Classification
Breast cancer is the malignant tumor that causes the highest number of cancer deaths in females.
Self-supervised Image Enhancement Network: Training with Low Light Images Only
We introduce a constraint that the maximum channel of the reflectance conforms to the maximum channel of the low light image and its entropy should be largest in our model to achieve self-supervised learning.
Learning Beam Codebooks with Neural Networks: Towards Environment-Aware mmWave MIMO
This leads to high beam training overhead and loss in the achievable beamforming gains.
Information Theory Signal Processing Information Theory
CODAR: A Contextual Duration-Aware Qubit Mapping for Various NISQ Devices
Quantum computing devices in the NISQ era share common features and challenges like limited connectivity between qubits.
Quantum Physics
High-Order Paired-ASPP Networks for Semantic Segmenation
The network first introduces a High-Order Representation module to extract the contextual high-order information from all stages of the backbone.
Deep Multi-Task Augmented Feature Learning via Hierarchical Graph Neural Network
The proposed feature augmentation strategy can be used in many deep multi-task learning models.
Deep Multi-Task Learning via Generalized Tensor Trace Norm
The GTTN is defined as a convex combination of matrix trace norms of all possible tensor flattenings and hence it can discover all the possible low-rank structures.
A Simple General Approach to Balance Task Difficulty in Multi-Task Learning
In multi-task learning, difficulty levels of different tasks are varying.
MDLdroid: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing
Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning for personal mobile sensing applications.
Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior
Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech.
Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis
This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model.
SpecAugment on Large Scale Datasets
Recently, SpecAugment, an augmentation scheme for automatic speech recognition that acts directly on the spectrogram of input utterances, has shown to be highly effective in enhancing the performance of end-to-end networks on public datasets.
Scalability in Perception for Autonomous Driving: Waymo Open Dataset
In an effort to help align the research community's contributions with real-world self-driving problems, we introduce a new large scale, high quality, diverse dataset.
Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models
In this paper, we propose to use pre-trained features from end-to-end ASR models to solve speech sentiment analysis as a down-stream task.
FeCaffe: FPGA-enabled Caffe with OpenCL for Deep Learning Training and Inference on Intel Stratix 10
In this paper, we firstly propose the FeCaffe, i. e. FPGA-enabled Caffe, a hierarchical software and hardware design methodology based on the Caffe to enable FPGA to support mainline deep learning development features, e. g. training and inference with Caffe.
Scale- and Context-Aware Convolutional Non-intrusive Load Monitoring
Non-intrusive load monitoring addresses the challenging task of decomposing the aggregate signal of a household's electricity consumption into appliance-level data without installing dedicated meters.
A comparison of end-to-end models for long-form speech recognition
In this paper, we both investigate and improve the performance of end-to-end models on long-form transcription.
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
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.
Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem.
Aspect-Based Sentiment Analysis
Unsupervised Domain Adaptation
Solving Optimization Problems through Fully Convolutional Networks: an Application to the Travelling Salesman Problem
Based on samples of a 10 city TSP, a fully convolutional network (FCN) is used to learn the mapping from a feasible region to an optimal solution.
ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
Furthermore, the unified design enables the integration of ASR functions with TTS, e. g., ASR-based objective evaluation and semi-supervised learning with both ASR and TTS models.
HiGitClass: Keyword-Driven Hierarchical Classification of GitHub Repositories
With the massive number of repositories available, there is a pressing need for topic-based search.
Deep Learning for Massive MIMO with 1-Bit ADCs: When More Antennas Need Fewer Pilots
This leads to the interesting, and \textit{counter-intuitive}, observation that when more antennas are employed by the massive MIMO base station, our proposed deep learning approach achieves better channel estimation performance, for the same pilot sequence length.
Information Theory Signal Processing Information Theory
End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds
In this paper, we aim to synergize the birds-eye view and the perspective view and propose a novel end-to-end multi-view fusion (MVF) algorithm, which can effectively learn to utilize the complementary information from both.
Knowledge Distillation from Internal Representations
In this paper, we propose to distill the internal representations of a large model such as BERT into a simplified version of it.
Speech Recognition with Augmented Synthesized Speech
Recent success of the Tacotron speech synthesis architecture and its variants in producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of replacing expensive, manually transcribed, domain-specific, human speech that is used to train speech recognizers.
Adversarial Representation Learning for Robust Patient-Independent Epileptic Seizure Detection
Furthermore, to enhance the explainability, we develop an attention mechanism to automatically learn the importance of each EEG channels in the seizure diagnosis procedure.
Gradient Q$(σ, λ)$: A Unified Algorithm with Function Approximation for Reinforcement Learning
To address above problem, we propose a GQ$(\sigma,\lambda)$ that extends tabular Q$(\sigma,\lambda)$ with linear function approximation.
Heterogeneous Domain Adaptation via Soft Transfer Network
Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain.
Multi-Spectral Visual Odometry without Explicit Stereo Matching
Moreover, the proposed method can also provide a metric 3D reconstruction in semi-dense density with multi-spectral information, which is not available from existing multi-spectral methods.
Discriminative Topic Mining via Category-Name Guided Text Embedding
We propose a new task, discriminative topic mining, which leverages a set of user-provided category names to mine discriminative topics from text corpora.
Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning
We present a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages.
Expected Sarsa($λ$) with Control Variate for Variance Reduction
In this paper, for reducing the variance, we introduce control variate technique to $\mathtt{Expected}$ $\mathtt{Sarsa}$($\lambda$) and propose a tabular $\mathtt{ES}$($\lambda$)-$\mathtt{CV}$ algorithm.
Policy Optimization with Stochastic Mirror Descent
Improving sample efficiency has been a longstanding goal in reinforcement learning.
Brain Network Construction and Classification Toolbox (BrainNetClass)
The goal of this work is to introduce a toolbox namely "Brain Network Construction and Classification" (BrainNetClass) to the field to promote more advanced brain network construction methods.