51 citations · 148 across the 42 of their papers we have counts for
44 papers
GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network
Panfeng Cao, Jian Wu
Key information extraction (KIE) from visually rich documents (VRD) has been a challenging task in document intelligence because of not only the complicated and diverse layouts of…
The second multi-channel multi-party meeting transcription challenge (M2MeT) 2.0): A benchmark for speaker-attributed ASR
Yuhao Liang, Mohan Shi, Fan Yu +11
With the success of the first Multi-channel Multi-party Meeting Transcription challenge (M2MeT), the second M2MeT challenge (M2MeT 2.0) held in ASRU2023 particularly aims to tackle…
GCL: Gradient-Guided Contrastive Learning for Medical Image Segmentation with Multi-Perspective Meta Labels
Yixuan Wu, Jintai Chen, Jiahuan Yan +3
Since annotating medical images for segmentation tasks commonly incurs expensive costs, it is highly desirable to design an annotation-efficient method to alleviate the annotation…
t-SOT FNT: Streaming Multi-talker ASR with Text-only Domain Adaptation Capability
Jian Wu, Naoyuki Kanda, Takuya Yoshioka +3
Token-level serialized output training (t-SOT) was recently proposed to address the challenge of streaming multi-talker automatic speech recognition (ASR). T-SOT effectively handle…
Profile-Error-Tolerant Target-Speaker Voice Activity Detection
Dongmei Wang, Xiong Xiao, Naoyuki Kanda +3
Target-Speaker Voice Activity Detection (TS-VAD) utilizes a set of speaker profiles alongside an input audio signal to perform speaker diarization. While its superiority over conve…
Can Large Language Models Discern Evidence for Scientific Hypotheses? Case Studies in the Social Sciences
Sai Koneru, Jian Wu, Sarah Rajtmajer
Hypothesis formulation and testing are central to empirical research. A strong hypothesis is a best guess based on existing evidence and informed by a comprehensive view of relevan…
Bilingual Streaming ASR with Grapheme units and Auxiliary Monolingual Loss
Mohammad Soleymanpour, Mahmoud Al Ismail, Fahimeh Bahmaninezhad +2
We introduce a bilingual solution to support English as secondary locale for most primary locales in hybrid automatic speech recognition (ASR) settings. Our key developments consti…
It's Not Just GitHub: Identifying Data and Software Sources Included in Publications
Emily Escamilla, Lamia Salsabil, Martin Klein +3
Paper publications are no longer the only form of research product. Due to recent initiatives by publication venues and funding institutions, open access datasets and software prod…
On decoder-only architecture for speech-to-text and large language model integration
Jian Wu, Yashesh Gaur, Zhuo Chen +8
Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. Howeve…
A Novel Correlation-optimized Deep Learning Method for Wind Speed Forecast
Yang Yang, Jin Lang, Jian Wu +2
The increasing installation rate of wind power poses great challenges to the global power system. In order to ensure the reliable operation of the power system, it is necessary to…
Enhancing Language Representation with Constructional Information for Natural Language Understanding
Lvxiaowei Xu, Jianwang Wu, Jiawei Peng +3
Natural language understanding (NLU) is an essential branch of natural language processing, which relies on representations generated by pre-trained language models (PLMs). However…
A Novel Black Box Process Quality Optimization Approach based on Hit Rate
Yang Yang, Jian Wu, Xiangman Song +3
Hit rate is a key performance metric in predicting process product quality in integrated industrial processes. It represents the percentage of products accepted by downstream proce…
TACR: A Table-alignment-based Cell-selection and Reasoning Model for Hybrid Question-Answering
Jian Wu, Yicheng Xu, Yan Gao +3
Hybrid Question-Answering (HQA), which targets reasoning over tables and passages linked from table cells, has witnessed significant research in recent years. A common challenge in…
A Study on Reproducibility and Replicability of Table Structure Recognition Methods
Kehinde Ajayi, Muntabir Hasan Choudhury, Sarah Rajtmajer +1
Concerns about reproducibility in artificial intelligence (AI) have emerged, as researchers have reported unsuccessful attempts to directly reproduce published findings in the fiel…
MetaEnhance: Metadata Quality Improvement for Electronic Theses and Dissertations of University Libraries
Muntabir Hasan Choudhury, Lamia Salsabil, Himarsha R. Jayanetti +3
Metadata quality is crucial for digital objects to be discovered through digital library interfaces. However, due to various reasons, the metadata of digital objects often exhibits…
Improving Transformer-based Networks With Locality For Automatic Speaker Verification
Mufan Sang, Yong Zhao, Gang Liu +2
Recently, Transformer-based architectures have been explored for speaker embedding extraction. Although the Transformer employs the self-attention mechanism to efficiently model th…
Speaker Change Detection for Transformer Transducer ASR
Jian Wu, Zhuo Chen, Min Hu +2
Speaker change detection (SCD) is an important feature that improves the readability of the recognized words from an automatic speech recognition (ASR) system by breaking the word…
ExcelFormer: A neural network surpassing GBDTs on tabular data
Jintai Chen, Jiahuan Yan, Qiyuan Chen +3
Data organized in tabular format is ubiquitous in real-world applications, and users often craft tables with biased feature definitions and flexibly set prediction targets of their…
Speech separation with large-scale self-supervised learning
Zhuo Chen, Naoyuki Kanda, Jian Wu +6
Self-supervised learning (SSL) methods such as WavLM have shown promising speech separation (SS) results in small-scale simulation-based experiments. In this work, we extend the ex…
Simulating realistic speech overlaps improves multi-talker ASR
Muqiao Yang, Naoyuki Kanda, Xiaofei Wang +5
Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the di…
Self-supervised learning with bi-label masked speech prediction for streaming multi-talker speech recognition
Zili Huang, Zhuo Chen, Naoyuki Kanda +6
Self-supervised learning (SSL), which utilizes the input data itself for representation learning, has achieved state-of-the-art results for various downstream speech tasks. However…
Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Experts
Xiaofei Wang, Zhuo Chen, Yu Shi +3
Employing a monaural speech separation (SS) model as a front-end for automatic speech recognition (ASR) involves balancing two kinds of trade-offs. First, while a larger model impr…
FCGEC: Fine-Grained Corpus for Chinese Grammatical Error Correction
Lvxiaowei Xu, Jianwang Wu, Jiawei Peng +2
Grammatical Error Correction (GEC) has been broadly applied in automatic correction and proofreading system recently. However, it is still immature in Chinese GEC due to limited hi…
VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition
Naoyuki Kanda, Jian Wu, Xiaofei Wang +3
This paper presents a novel streaming automatic speech recognition (ASR) framework for multi-talker overlapping speech captured by a distant microphone array with an arbitrary geom…