b'Wei Han'

research

∙ 09/19/2023

Multimodal Modeling For Spoken Language Identification

Spoken language identification refers to the task of automatically predi...

0 Shikhar Bharadwaj, et al. ∙

research

∙ 07/09/2023

SAS Video-QA: Self-Adaptive Sampling for Efficient Video Question-Answering

Video question–answering is a fundamental task in the field of video und...

0 Wei Han, et al. ∙

research

∙ 06/22/2023

AudioPaLM: A Large Language Model That Can Speak and Listen

We introduce AudioPaLM, a large language model for speech understanding ...

0 Paul K. Rubenstein, et al. ∙

research

∙ 06/08/2023

Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding

Large Language Models (LLMs) have been applied in the speech domain, oft...

0 Mingqiu Wang, et al. ∙

research

∙ 06/07/2023

Label Aware Speech Representation Learning For Language Identification

Speech representation learning approaches for non-semantic tasks such as...

0 Shikhar Vashishth, et al. ∙

research

∙ 05/30/2023

LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus

This paper introduces a new speech dataset called “LibriTTS-R” designed ...

0 Yuma Koizumi, et al. ∙

research

∙ 05/23/2023

Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction

Aspect Sentiment Triplet Extraction (ASTE) is a subtask of Aspect-Based ...

0 Yew Ken Chia, et al. ∙

research

∙ 05/16/2023

Conditional Rate-Distortion-Perception Trade-Off

Recent advances in machine learning-aided lossy compression are incorpor...

0 Xueyan Niu, et al. ∙

research

∙ 05/13/2023

Power Allocation for the Base Matrix of Spatially Coupled Sparse Regression Codes

We investigate power allocation for the base matrix of a spatially coupl...

0 Nian Guo, et al. ∙

research

∙ 03/23/2023

Modular CSI Quantization for FDD Massive MIMO Communication

We consider high-dimensional MIMO transmissions in frequency division du...

0 Jialing Liao, et al. ∙

research

∙ 03/03/2023

Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations

Speech restoration (SR) is a task of converting degraded speech signals ...

0 Yuma Koizumi, et al. ∙

research

∙ 03/02/2023

Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

We introduce the Universal Speech Model (USM), a single large model that...

0 Yu Zhang, et al. ∙

research

∙ 02/08/2023

Noise2Music: Text-conditioned Music Generation with Diffusion Models

We introduce Noise2Music, where a series of diffusion models is trained ...

0 Qingqing Huang, et al. ∙

research

∙ 01/13/2023

Electromagnetic-Compliant Channel Modeling and Performance Evaluation for Holographic MIMO

Recently, the concept of holographic multiple-input multiple-output (MIM...

0 Tengjiao Wang, et al. ∙

research

∙ 12/16/2022

Speech Aware Dialog System Technology Challenge (DSTC11)

Most research on task oriented dialog modeling is based on written text ...

0 Hagen Soltau, et al. ∙

research

∙ 11/14/2022

An Interpretable Neuron Embedding for Static Knowledge Distillation

Although deep neural networks have shown well-performance in various tas...

0 Wei Han, et al. ∙

research

∙ 10/29/2022

Accelerating RNN-T Training and Inference Using CTC guidance

We propose a novel method to accelerate training and inference process o...

0 Yongqiang Wang, et al. ∙

research

∙ 10/23/2022

MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences

Existing multimodal tasks mostly target at the complete input modality s...

0 Wei Han, et al. ∙

research

∙ 10/23/2022

SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training

Self-training methods have been explored in recent years and have exhibi...

0 Hui Chen, et al. ∙

research

∙ 09/12/2022

DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification

This paper proposes a simple yet effective interpolation-based data augm...

0 Hui Chen, et al. ∙

research

∙ 09/12/2022

SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning

With the boom of e-commerce, Multimodal Review Helpfulness Prediction (M...

0 Wei Han, et al. ∙

research

∙ 08/12/2022

Semantic Compression with Side Information: A Rate-Distortion Perspective

We consider the semantic rate-distortion problem motivated by task-orien...

0 Tao Guo, et al. ∙

research

∙ 06/22/2022

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

We present the Pathways Autoregressive Text-to-Image (Parti) model, whic...

0 Jiahui Yu, et al. ∙

research

∙ 05/17/2022

Lossy Computing with Side Information via Multi-Hypergraphs

We consider a problem of coding for computing, where the decoder wishes ...

0 Deheng Yuan, et al. ∙

research

∙ 05/16/2022

Accented Speech Recognition: Benchmarking, Pre-training, and Diverse Data

Building inclusive speech recognition systems is a crucial step towards ...

0 Alëna Aksënova, et al. ∙

research

∙ 04/07/2022

TOSE: A Fast Capacity Determination Algorithm Based on Random Matrix Theory

Wireless network capacity is one of the most important performance metri...

0 Dandan Jiang, et al. ∙

research

∙ 03/08/2022

An Efficient Two-Stage SPARC Decoder for Massive MIMO Unsourced Random Access

In this paper, we study a concatenate coding scheme based on sparse regr...

0 Juntao You, et al. ∙

research

∙ 12/14/2021

Co-training Transformer with Videos and Images Improves Action Recognition

In learning action recognition, models are typically pre-trained on obje...

0 Bowen Zhang, et al. ∙

research

∙ 11/01/2021

Algorithms for Interference Minimization in Future Wireless Network Decomposition

We propose a simple and fast method for providing a high quality solutio...

0 Péter L. Erdős, et al. ∙

research

∙ 10/25/2021

TAPL: Dynamic Part-based Visual Tracking via Attention-guided Part Localization

Holistic object representation-based trackers suffer from performance dr...

0 Wei Han, et al. ∙

research

∙ 10/09/2021

Universal Paralinguistic Speech Representations Using Self-Supervised Conformers

Many speech applications require understanding aspects beyond the words ...

0 Joel Shor, et al. ∙

research

∙ 10/08/2021

Multi-trends Enhanced Dynamic Micro-video Recommendation

The explosively generated micro-videos on content sharing platforms call...

0 Yujie Lu, et al. ∙

research

∙ 10/07/2021

What Should Future Wireless Network Architectures Be?

The accelerated convergence of digital and real-world lifestyles has imp...

0 Lu Yang, et al. ∙

research

∙ 09/27/2021

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 spee...

1 Yu Zhang, et al. ∙

research

∙ 09/01/2021

Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis

In multimodal sentiment analysis (MSA), the performance of a model highl...

0 Wei Han, et al. ∙

research

∙ 08/07/2021

W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training

Motivated by the success of masked language modeling (MLM) in pre-traini...

0 Yu-An Chung, et al. ∙

research

∙ 07/28/2021

Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis

Multimodal sentiment analysis aims to extract and integrate semantic inf...

13 Wei Han, et al. ∙

research

∙ 07/02/2021

Supervised Contrastive Learning for Accented Speech Recognition

Neural network based speech recognition systems suffer from performance ...

0 Tao Han, et al. ∙

research

∙ 04/25/2021

Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models

Streaming end-to-end automatic speech recognition (ASR) systems are wide...

0 Thibault Doutre, et al. ∙

research

∙ 04/06/2021

Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models

Although end-to-end automatic speech recognition (e2e ASR) models are wi...

0 Zhiyun Lu, et al. ∙

research

∙ 11/21/2020

A Better and Faster End-to-End Model for Streaming ASR

End-to-end (E2E) models have shown to outperform state-of-the-art conven...

0 Bo Li, et al. ∙

research

∙ 10/22/2020

Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data

Streaming end-to-end automatic speech recognition (ASR) models are widel...

0 Thibault Doutre, et al. ∙

research

∙ 10/21/2020

FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization

Streaming automatic speech recognition (ASR) aims to emit each hypothesi...

5 Jiahui Yu, et al. ∙

research

∙ 10/20/2020

Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition

We employ a combination of recent developments in semi-supervised learni...

0 Yu Zhang, et al. ∙

research

∙ 10/17/2020

Answer-checking in Context: A Multi-modal FullyAttention Network for Visual Question Answering

Visual Question Answering (VQA) is challenging due to the complex cross-...

0 Hantao Huang, et al. ∙

research

∙ 10/12/2020

Universal ASR: Unify and Improve Streaming ASR with Full-context Modeling

Streaming automatic speech recognition (ASR) aims to emit each hypothesi...

8 Jiahui Yu, et al. ∙

research

∙ 10/06/2020

Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering

Image text carries essential information to understand the scene and per...

0 Wei Han, et al. ∙

research

∙ 09/10/2020

Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks

Dialogue relation extraction (DRE) aims to detect the relation between t...

0 Hui Chen, et al. ∙

research

∙ 06/02/2020

Rate-Splitting Multiple Access: A New Frontier for the PHY Layer of 6G

This paper argues that to efficiently cope with the high throughput, rel...

0 Onur Dizdar, et al. ∙

research

∙ 05/27/2020

Rate-Splitting Multiple Access for Downlink Multi-Antenna Communications: Physical Layer Design and Link-level Simulations

Rate-Splitting Multiple Access (RSMA) is an emerging flexible, robust an...

0 Onur Dizdar, et al. ∙

Wei Han

Featured Co-authors