9 citations · 15 across the 8 of their papers we have counts for
8 papers
Multimodal Tree Decoder for Table of Contents Extraction in Document Images
Pengfei Hu, Zhenrong Zhang, Jianshu Zhang +2
Table of contents (ToC) extraction aims to extract headings of different levels in documents to better understand the outline of the contents, which can be widely used for document…
Learning Audio-Visual embedding for Person Verification in the Wild
Peiwen Sun, Shanshan Zhang, Zishan Liu +4
It has already been observed that audio-visual embedding is more robust than uni-modality embedding for person verification. Here, we proposed a novel audio-visual strategy that co…
Defensive Patches for Robust Recognition in the Physical World
Jiakai Wang, Zixin Yin, Pengfei Hu +5
To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which impro…
Leveraging Phone Mask Training for Phonetic-Reduction-Robust E2E Uyghur Speech Recognition
Guodong Ma, Pengfei Hu, Jian Kang +2
In Uyghur speech, consonant and vowel reduction are often encountered, especially in spontaneous speech with high speech rate, which will cause a degradation of speech recognition…
Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition
Qijie Shao, Jinghao Yan, Jian Kang +4
General accent recognition (AR) models tend to directly extract low-level information from spectrums, which always significantly overfit on speakers or channels. Considering accent…
MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification
Yang Zhang, Zhiqiang Lv, Haibin Wu +5
In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on…
PM-MMUT: Boosted Phone-Mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition
Guodong Ma, Pengfei Hu, Nurmemet Yolwas +2
Consonant and vowel reduction are often encountered in speech, which might cause performance degradation in automatic speech recognition (ASR). Our recently proposed learning strat…
VRM-Phase I VKW system description of long-short video customizable keyword wakeup challenge
Yougen Yuan, Zhiqiang Lv, Shen Huang +1
Keyword wakeup technology has always been a research hotspot in speech processing, but many related works were done on different datasets. We organized a Chinese long-short video k…