57 citations · 82 across the 11 of their papers we have counts for
11 papers
Filler Word Detection with Hard Category Mining and Inter-Category Focal Loss
Zhiyuan Zhao, Lijun Wu, Chuanxin Tang +3
Filler words like ``um" or ``uh" are common in spontaneous speech. It is desirable to automatically detect and remove them in recordings, as they affect the fluency, confidence, an…
Streaming Video Model
Yucheng Zhao, Chong Luo, Chuanxin Tang +3
Video understanding tasks have traditionally been modeled by two separate architectures, specially tailored for two distinct tasks. Sequence-based video tasks, such as action recog…
Look Before You Match: Instance Understanding Matters in Video Object Segmentation
Junke Wang, Dongdong Chen, Zuxuan Wu +7
Exploring dense matching between the current frame and past frames for long-range context modeling, memory-based methods have demonstrated impressive results in video object segmen…
TridentSE: Guiding Speech Enhancement with 32 Global Tokens
Dacheng Yin, Zhiyuan Zhao, Chuanxin Tang +2
In this paper, we present TridentSE, a novel architecture for speech enhancement, which is capable of efficiently capturing both global information and local details. TridentSE mai…
An Anchor-Free Detector for Continuous Speech Keyword Spotting
Zhiyuan Zhao, Chuanxin Tang, Chengdong Yao +1
Continuous Speech Keyword Spotting (CSKWS) is a task to detect predefined keywords in a continuous speech. In this paper, we regard CSKWS as a one-dimensional object detection task…
RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion
Dacheng Yin, Chuanxin Tang, Yanqing Liu +6
This paper proposes a new "decompose-and-edit" paradigm for the text-based speech insertion task that facilitates arbitrary-length speech insertion and even full sentence generatio…
When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism
Guangting Wang, Yucheng Zhao, Chuanxin Tang +2
Attention mechanism has been widely believed as the key to success of vision transformers (ViTs), since it provides a flexible and powerful way to model spatial relationships. Howe…
Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
Chuanxin Tang, Chong Luo, Zhiyuan Zhao +3
Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript.…
Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?
Chuanxin Tang, Yucheng Zhao, Guangting Wang +3
Transformers have sprung up in the field of computer vision. In this work, we explore whether the core self-attention module in Transformer is the key to achieving excellent perfor…
A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP
Yucheng Zhao, Guangting Wang, Chuanxin Tang +3
Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision. Recently, Transformer and multi-layer perceptron (MLP)-based models…
General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework
Yucheng Zhao, Dacheng Yin, Chong Luo +4
This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. In the design of MGF, speech hierarchy is taken into consid…