Search Results for author:
Found 81 papers, 28 papers with code
SmartCiteCon: Implicit Citation Context Extraction from Academic Literature Using Supervised Learning
The tool is built on a Support Vector Machine (SVM) model trained on a set of 7, 058 manually annotated citation context sentences, curated from 34, 000 papers from the ACL Anthology.
Acknowledgement Entity Recognition in CORD-19 Papers
We built a supplementary database by linking CORD-19 papers with acknowledgement entities extracted by AckExtract including persons and organizations and find that only up to 50–60% of named entities are actually acknowledged.
Deploying self-supervised learning in the wild for hybrid automatic speech recognition
Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR).
Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation
Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design.
SciEv: Finding Scientific Evidence Papers for Scientific News
To our best knowledge, this is the first dataset of this kind.
Ultra Fast Speech Separation Model with Teacher Student Learning
In this paper, an ultra fast speech separation Transformer model is proposed to achieve both better performance and efficiency with teacher student learning (T-S learning).
Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?
Recently, self-supervised learning (SSL) has demonstrated strong performance in speaker recognition, even if the pre-training objective is designed for speech recognition.
Online Deep Learning from Doubly-Streaming Data
This paper investigates a new online learning problem with doubly-streaming data, where the data streams are described by feature spaces that constantly evolve, with new features emerging and old features fading away.
Attention-based CNN-LSTM and XGBoost hybrid model for stock prediction
Due to the complex volatility of the stock market, the research and prediction on the change of the stock price, can avoid the risk for the investors.
Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings
The proposed speaker embedding, named t-vector, is extracted synchronously with the t-SOT ASR model, enabling joint execution of speaker identification (SID) or speaker diarization (SD) with the multi-talker transcription with low latency.
Large-Scale 3D Semantic Reconstruction for Automated Driving Vehicles with Adaptive Truncated Signed Distance Function
Since a 3D surface can be usually observed from multiple camera images with different view poses, an optimal image patch selection for the texturing and an optimal semantic class estimation for the semantic mapping are still challenging.
DialMed: A Dataset for Dialogue-based Medication Recommendation
Therefore, we make the first attempt to recommend medications with the conversations between doctors and patients.
A State-of-the-art Survey of U-Net in Microscopic Image Analysis: from Simple Usage to Structure Mortification
Image analysis technology is used to solve the inadvertences of artificial traditional methods in disease, wastewater treatment, environmental change monitoring analysis and convolutional neural networks (CNN) play an important role in microscopic image analysis.
Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study
An Xception model reaches state-of-the-art (SOTA) accuracy on the ESC-50 dataset for audio event detection through knowledge transfer from ImageNet weights, pretraining on AudioSet, and an on-the-fly data augmentation pipeline.
Streaming Multi-Talker ASR with Token-Level Serialized Output Training
This paper proposes a token-level serialized output training (t-SOT), a novel framework for streaming multi-talker automatic speech recognition (ASR).
What Can Machine Vision Do for Lymphatic Histopathology Image Analysis: A Comprehensive Review
In the past ten years, the computing power of machine vision (MV) has been continuously improved, and image analysis algorithms have developed rapidly.
D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentation
In this paper, we propose a new method called Dilated Transformer, which conducts self-attention for pair-wise patch relations captured alternately in local and global scopes.
PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving
The accelerating development of autonomous driving technology has placed greater demands on obtaining large amounts of high-quality data.
A Synthetic Prediction Market for Estimating Confidence in Published Work
Explainably estimating confidence in published scholarly work offers opportunity for faster and more robust scientific progress.
AGMI: Attention-Guided Multi-omics Integration for Drug Response Prediction with Graph Neural Networks
Accurate drug response prediction (DRP) is a crucial yet challenging task in precision medicine.
DANets: Deep Abstract Networks for Tabular Data Classification and Regression
A special basic block is built using AbstLays, and we construct a family of Deep Abstract Networks (DANets) for tabular data classification and regression by stacking such blocks.
Continuous Speech Separation with Recurrent Selective Attention Network
In this paper, we propose to apply recurrent selective attention network (RSAN) to CSS, which generates a variable number of output channels based on active speaker counting.
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks.
UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training
We integrate the proposed methods into the HuBERT framework.
A Neural Network-Based Linguistic Similarity Measure for Entrainment in Conversations
Then we use the model to perform similarity measure in a corpus-based entrainment analysis.
A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio
Our evaluation on the AMI meeting corpus reveals that after fine-tuning with a small real data, the joint system performs 8. 9--29. 9% better in accuracy compared to the best modular system while the modular system performs better before such fine-tuning.
Investigation of Practical Aspects of Single Channel Speech Separation for ASR
Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic speech recognition (ASR).
Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations
Our experiments show that CRF with visual features outperformed both a heuristic and a CRF model with only text-based features.
Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models
We propose a cost-effective method of using CC scores to select an optimal adaptation data set, where we maximize ASR gains from minimal data.
ScanBank: A Benchmark Dataset for Figure Extraction from Scanned Electronic Theses and Dissertations
To the best of our knowledge, ScanBank is the first manually annotated dataset for figure and table extraction for scanned ETDs.
Extractive Research Slide Generation Using Windowed Labeling Ranking
Presentation slides describing the content of scientific and technical papers are an efficient and effective way to present that work.
Document Domain Randomization for Deep Learning Document Layout Extraction
We present document domain randomization (DDR), the first successful transfer of convolutional neural networks (CNNs) trained only on graphically rendered pseudo-paper pages to real-world document segmentation.
Electrocardio Panorama: Synthesizing New ECG Views with Self-supervision
For the first time, we propose a new concept, Electrocardio Panorama, which allows visualizing ECG signals from any queried viewpoints.
Predicting the Reproducibility of Social and Behavioral Science Papers Using Supervised Learning Models
In this paper, we investigate prediction of the reproducibility of SBS papers using machine learning methods based on a set of features.
A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches
This paper reviews the methods of WSI analysis based on machine learning.
Doctor Imitator: A Graph-based Bone Age Assessment Framework Using Hand Radiographs
The architecture of DI is designed to learn the diagnostic logistics of doctors using the scoring methods (e. g., the Tanner-Whitehouse method) for bone age assessment.
Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels
In clinical practice, medical image interpretation often involves multi-labeled classification, since the affected parts of a patient tend to present multiple symptoms or comorbidities.
Speaker attribution with voice profiles by graph-based semi-supervised learning
Speaker attribution is required in many real-world applications, such as meeting transcription, where speaker identity is assigned to each utterance according to speaker voice profiles.
Modeling Updates of Scholarly Webpages Using Archived Data
The vastness of the web imposes a prohibitive cost on building large-scale search engines with limited resources.
Reconstruction Condition of Quantized Signals in Unlimited Sampling Framework
The latest theoretical advances in the field of unlimited sampling framework (USF) show the potential to avoid clipping problems of analog-to-digital converters (ADC).
IEEE SLT 2021 Alpha-mini Speech Challenge: Open Datasets, Tracks, Rules and Baselines
In this challenge, we open source a sizable speech, keyword, echo and noise corpus for promoting data-driven methods, particularly deep-learning approaches on KWS and SSL.
Sound Audio and Speech Processing
Multi-View Adaptive Fusion Network for 3D Object Detection
3D object detection based on LiDAR-camera fusion is becoming an emerging research theme for autonomous driving.
Dynamic radiomics: a new methodology to extract quantitative time-related features from tomographic images
The feature extraction methods of radiomics are mainly based on static tomographic images at a certain moment, while the occurrence and development of disease is a dynamic process that cannot be fully reflected by only static characteristics.
An End-to-end Architecture of Online Multi-channel Speech Separation
Previously, we introduced a sys-tem, calledunmixing, fixed-beamformerandextraction(UFE), that was shown to be effective in addressing the speech over-lap problem in conversation transcription.
Preference Robust Optimization with Quasi-Concave Choice Functions for Multi-Attribute Prospects
Preference robust choice models concern decision-making problems where the decision maker's (DM) utility/risk preferences are ambiguous and the evaluation is based on the worst-case utility function/risk measure from a set of plausible utility functions/risk measures.
Echoes in Unidirectionally Rotating Molecules
Abstract We report the experimental observation of molecular unidirectional rotation (UDR) echoes, and analyze their origin and behavior both classically and quantum mechanically.
Optics
Continuous Speech Separation with Conformer
Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription.
Channel-wise Subband Input for Better Voice and Accompaniment Separation on High Resolution Music
We aim to address the major issues in CNN-based high-resolution MSS model: high computational cost and weight sharing between distinctly different bands.
Audio and Speech Processing Sound
DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement
Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality.
Ranked #3 on
Speech Enhancement
on Deep Noise Suppression (DNS) Challenge
(PESQ-NB metric)
Speech Enhancement
Audio and Speech Processing
Sound
Large Scale Subject Category Classification of Scholarly Papers with Deep Attentive Neural Networks
The results showed the importance of retraining word embedding models to maximize the vocabulary overlap and the effectiveness of the attention mechanism.
CenterNet3D: An Anchor Free Object Detector for Point Cloud
However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries.
Speaker diarization with session-level speaker embedding refinement using graph neural networks
Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be sub-optimal for distinguishing speakers locally in a specific meeting session.
UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation
UNet, which is one of deep learning networks with an encoder-decoder architecture, is widely used in medical image segmentation.
Ranked #1 on
Medical Image Segmentation
on LiTS2017
Continuous speech separation: dataset and analysis
In this paper, we define continuous speech separation (CSS) as a task of generating a set of non-overlapped speech signals from a \textit{continuous} audio stream that contains multiple utterances that are \emph{partially} overlapped by a varying degree.
Audio-visual Recognition of Overlapped speech for the LRS2 dataset
Experiments on overlapped speech simulated from the LRS2 dataset suggest the proposed AVSR system outperformed the audio only baseline LF-MMI DNN system by up to 29. 98\% absolute in word error rate (WER) reduction, and produced recognition performance comparable to a more complex pipelined system.
Ranked #7 on
Lipreading
on LRS2
(using extra training data)
Query Auto Completion for Math Formula Search
Query Auto Completion (QAC) is among the most appealing features of a web search engine.
Practical Two-Step Lookahead Bayesian Optimization
Expected improvement and other acquisition functions widely used in Bayesian optimization use a "one-step" assumption: they value objective function evaluations assuming no future evaluations will be performed.
Method and Dataset Mining in Scientific Papers
In the field of machine learning, the involved methods (M) and datasets (D) are key information in papers.
Privileged Features Distillation at Taobao Recommendations
To guarantee the consistency of off-line training and on-line serving, we usually utilize the same features that are both available.
Dunhuang Grottoes Painting Dataset and Benchmark
Follow the trend, we release the first public dataset for Dunhuang Grotto Painting restoration.
Cleaning Noisy and Heterogeneous Metadata for Record Linking Across Scholarly Big Datasets
We introduce a system designed to match scholarly document entities with noisy metadata against a reference dataset.
A comprehensive study of speech separation: spectrogram vs waveform separation
We study the speech separation problem for far-field data (more similar to naturalistic audio streams) and develop multi-channel solutions for both frequency and time-domain separators with utilizing spectral, spatial and speaker location information.
X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks
Computed tomography (CT) can provide a 3D view of the patient's internal organs, facilitating disease diagnosis, but it incurs more radiation dose to a patient and a CT scanner is much more cost prohibitive than an X-ray machine too.
End-to-End Multi-Channel Speech Separation
This paper extended the previous approach and proposed a new end-to-end model for multi-channel speech separation.
Personalized Re-ranking for Recommendation
Ranking is a core task in recommender systems, which aims at providing an ordered list of items to users.
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
To address this problem, we train the bidirectional model using the Cloze task, predicting the masked items in the sequence by jointly conditioning on their left and right context.
Time Domain Audio Visual Speech Separation
Audio-visual multi-modal modeling has been demonstrated to be effective in many speech related tasks, such as speech recognition and speech enhancement.
Audio and Speech Processing Sound
Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning
Nonetheless, for hyperparameter tuning in deep neural networks, the time required to evaluate the validation error for even a few hyperparameter settings remains a bottleneck.
Improving Automatic Source Code Summarization via Deep Reinforcement Learning
To the best of our knowledge, most state-of-the-art approaches follow an encoder-decoder framework which encodes the code into a hidden space and then decode it into natural language space, suffering from two major drawbacks: a) Their encoders only consider the sequential content of code, ignoring the tree structure which is also critical for the task of code summarization, b) Their decoders are typically trained to predict the next word by maximizing the likelihood of next ground-truth word with previous ground-truth word given.
Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training
Dialogue Act (DA) classification is a challenging problem in dialogue interpretation, which aims to attach semantic labels to utterances and characterize the speaker's intention.
Ranked #4 on
Dialogue Act Classification
on Switchboard corpus
Learned Neural Iterative Decoding for Lossy Image Compression Systems
For lossy image compression systems, we develop an algorithm, iterative refinement, to improve the decoder's reconstruction compared to standard decoding techniques.
Continuous-fidelity Bayesian Optimization with Knowledge Gradient
While Bayesian optimization (BO) has achieved great success in optimizing expensive-to-evaluate black-box functions, especially tuning hyperparameters of neural networks, methods such as random search (Li et al., 2016) and multi-fidelity BO (e. g. Klein et al. (2017)) that exploit cheap approximations, e. g. training on a smaller training data or with fewer iterations, can outperform standard BO approaches that use only full-fidelity observations.
A Hierarchical Recurrent Neural Network for Symbolic Melody Generation
In this paper, we present a hierarchical recurrent neural network for melody generation, which consists of three Long-Short-Term-Memory (LSTM) subnetworks working in a coarse-to-fine manner along time.
Sound Multimedia
Discretization-free Knowledge Gradient Methods for Bayesian Optimization
This paper studies Bayesian ranking and selection (R&S) problems with correlated prior beliefs and continuous domains, i. e. Bayesian optimization (BO).
Bayesian Optimization with Gradients
Bayesian optimization has been successful at global optimization of expensive-to-evaluate multimodal objective functions.
The Parallel Knowledge Gradient Method for Batch Bayesian Optimization
In many applications of black-box optimization, one can evaluate multiple points simultaneously, e. g. when evaluating the performances of several different neural network architectures in a parallel computing environment.
Multi-modal Fusion for Diabetes Mellitus and Impaired Glucose Regulation Detection
has proved that tongue, face and sublingual diagnosis as a noninvasive method is a reasonable way for disease detection.
