204 citations · 784 across the 42 of their papers we have counts for
42 papers
FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction
Yitong Duan, Weiran Wang, Jian Li
As a fundamental method in economics and finance, the factor model has been extensively utilized in quantitative investment. In recent years, there has been a paradigm shift from t…
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
Junwen Bai, Weiran Wang, Yingbo Zhou +1
We propose Deep Autoencoding Predictive Components (DAPC) -- a self-supervised representation learning method for sequence data, based on the intuition that useful representations…
An investigation of phone-based subword units for end-to-end speech recognition
Weiran Wang, Guangsen Wang, Aadyot Bhatnagar +3
Phones and their context-dependent variants have been the standard modeling units for conventional speech recognition systems, while characters and subwords have demonstrated their…
A Comparison of Pooling Methods on LSTM Models for Rare Acoustic Event Classification
Chieh-Chi Kao, Ming Sun, Weiran Wang +1
Acoustic event classification (AEC) and acoustic event detection (AED) refer to the task of detecting whether specific target events occur in audios. As long short-term memory (LST…
Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction
Weiran Wang, Qingming Tang, Karen Livescu
We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used direct…
Data Techniques For Online End-to-end Speech Recognition
Yang Chen, Weiran Wang, I-Fan Chen +1
Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data. While recently developed end-to-end methods largely simplif…
Semi-supervised ASR by End-to-end Self-training
Yang Chen, Weiran Wang, Chao Wang
While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work,…
Acoustic scene analysis with multi-head attention networks
Weimin Wang, Weiran Wang, Ming Sun +1
Acoustic Scene Classification (ASC) is a challenging task, as a single scene may involve multiple events that contain complex sound patterns. For example, a cooking scene may conta…
Multimodal and Multi-view Models for Emotion Recognition
Gustavo Aguilar, Viktor Rozgić, Weiran Wang +1
Studies on emotion recognition (ER) show that combining lexical and acoustic information results in more robust and accurate models. The majority of the studies focus on settings w…
Everything old is new again: A multi-view learning approach to learning using privileged information and distillation
Weiran Wang
We adopt a multi-view approach for analyzing two knowledge transfer settings---learning using privileged information (LUPI) and distillation---in a common framework. Under reasonab…
A simple model for detection of rare sound events
Weiran Wang, Chieh-chi Kao, Chao Wang
We propose a simple recurrent model for detecting rare sound events, when the time boundaries of events are available for training. Our model optimizes the combination of an uttera…
R-CRNN: Region-based Convolutional Recurrent Neural Network for Audio Event Detection
Chieh-Chi Kao, Weiran Wang, Ming Sun +1
This paper proposes a Region-based Convolutional Recurrent Neural Network (R-CRNN) for audio event detection (AED). The proposed network is inspired by Faster-RCNN, a well known re…
Acoustic feature learning using cross-domain articulatory measurements
Qingming Tang, Weiran Wang, Karen Livescu
Previous work has shown that it is possible to improve speech recognition by learning acoustic features from paired acoustic-articulatory data, for example by using canonical corre…
Distributed Stochastic Multi-Task Learning with Graph Regularization
Weiran Wang, Jialei Wang, Mladen Kolar +1
We propose methods for distributed graph-based multi-task learning that are based on weighted averaging of messages from other machines. Uniform averaging or diminishing stepsize i…
Stochastic Nonconvex Optimization with Large Minibatches
Weiran Wang, Nathan Srebro
We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimi…
Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis
Qingming Tang, Weiran Wang, Karen Livescu
We study the problem of acoustic feature learning in the setting where we have access to another (non-acoustic) modality for feature learning but not at test time. We use deep vari…
Efficient coordinate-wise leading eigenvector computation
Jialei Wang, Weiran Wang, Dan Garber +1
We develop and analyze efficient "coordinate-wise" methods for finding the leading eigenvector, where each step involves only a vector-vector product. We establish global convergen…
Stochastic Canonical Correlation Analysis
Chao Gao, Dan Garber, Nathan Srebro +2
We study the sample complexity of canonical correlation analysis (CCA), \ie, the number of samples needed to estimate the population canonical correlation and directions up to arbi…
Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch-Prox
Jialei Wang, Weiran Wang, Nathan Srebro
We present and analyze an approach for distributed stochastic optimization which is statistically optimal and achieves near-linear speedups (up to logarithmic factors). Our approac…
Multi-view Recurrent Neural Acoustic Word Embeddings
Wanjia He, Weiran Wang, Karen Livescu
Recent work has begun exploring neural acoustic word embeddings---fixed-dimensional vector representations of arbitrary-length speech segments corresponding to words. Such embeddin…
End-to-End Training Approaches for Discriminative Segmental Models
Hao Tang, Weiran Wang, Kevin Gimpel +1
Recent work on discriminative segmental models has shown that they can achieve competitive speech recognition performance, using features based on deep neural frame classifiers. Ho…
Deep Variational Canonical Correlation Analysis
Weiran Wang, Xinchen Yan, Honglak Lee +1
We present deep variational canonical correlation analysis (VCCA), a deep multi-view learning model that extends the latent variable model interpretation of linear CCA to nonlinear…
Lexicon-Free Fingerspelling Recognition from Video: Data, Models, and Signer Adaptation
Taehwan Kim, Jonathan Keane, Weiran Wang +5
We study the problem of recognizing video sequences of fingerspelled letters in American Sign Language (ASL). Fingerspelling comprises a significant but relatively understudied par…
Efficient Segmental Cascades for Speech Recognition
Hao Tang, Weiran Wang, Kevin Gimpel +1
Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational require…