English
Related papers

Related papers: Unified Segment-to-Segment Framework for Simultane…

200 papers

Generative modeling has recently achieved remarkable success across image, video, and audio domains, demonstrating powerful capabilities for unified representation learning. Yet speech front-end tasks such as speech enhancement (SE), target…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-12 Ziqian Wang , Zikai Liu , Yike Zhu , Xingchen Li , Boyi Kang , Jixun Yao , Xianjun Xia , Chuanzeng Huang , Lei Xie

Defect segmentation is crucial for quality control in advanced manufacturing, yet data scarcity poses challenges for state-of-the-art supervised deep learning. Synthetic defect data generation is a popular approach for mitigating data…

Computer Vision and Pattern Recognition · Computer Science 2024-10-25 Shancong Mou , Raviteja Vemulapalli , Shiyu Li , Yuxuan Liu , C Thomas , Meng Cao , Haoping Bai , Oncel Tuzel , Ping Huang , Jiulong Shan , Jianjun Shi

Most existing text generation models follow the sequence-to-sequence paradigm. Generative Grammar suggests that humans generate natural language texts by learning language grammar. We propose a syntax-guided generation schema, which…

Computation and Language · Computer Science 2023-06-27 Yafu Li , Leyang Cui , Jianhao Yan , Yongjing Yin , Wei Bi , Shuming Shi , Yue Zhang

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

Computer Vision and Pattern Recognition · Computer Science 2019-04-29 Amlan Kar , Aayush Prakash , Ming-Yu Liu , Eric Cameracci , Justin Yuan , Matt Rusiniak , David Acuna , Antonio Torralba , Sanja Fidler

In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models. Specifically, we achieve dynamic latency with only one model by using arbitrary right context during…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-04 Mingkun Huang , Meng Cai , Jun Zhang , Yang Zhang , Yongbin You , Yi He , Zejun Ma

Generative modeling of time series is a central challenge in time series analysis, particularly under data-scarce conditions. Despite recent advances in generative modeling, a comprehensive understanding of how state-of-the-art generative…

Machine Learning · Computer Science 2025-05-28 Tal Gonen , Itai Pemper , Ilan Naiman , Nimrod Berman , Omri Azencot

The latest emerged 4D Panoptic Scene Graph (4D-PSG) provides an advanced-ever representation for comprehensively modeling the dynamic 4D visual real world. Unfortunately, current pioneering 4D-PSG research can primarily suffer from data…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Shengqiong Wu , Hao Fei , Jingkang Yang , Xiangtai Li , Juncheng Li , Hanwang Zhang , Tat-seng Chua

Extending the context length (i.e., the maximum supported sequence length) of LLMs is of paramount significance. To facilitate long context training of LLMs, sequence parallelism has emerged as an essential technique, which scatters each…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-12 Yujie Wang , Shiju Wang , Shenhan Zhu , Fangcheng Fu , Xinyi Liu , Xuefeng Xiao , Huixia Li , Jiashi Li , Faming Wu , Bin Cui

A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware…

Computation and Language · Computer Science 2021-09-14 Hongru Wang , Mingyu Cui , Zimo Zhou , Gabriel Pui Cheong Fung , Kam-Fai Wong

Prompt learning is an effective paradigm that bridges gaps between the pre-training tasks and the corresponding downstream applications. Approaches based on this paradigm have achieved great transcendent results in various applications.…

Information Retrieval · Computer Science 2022-09-26 Zhigang Kan , Linhui Feng , Zhangyue Yin , Linbo Qiao , Xipeng Qiu , Dongsheng Li

Unified understanding and generation is a highly appealing research direction in multimodal learning. There exist two approaches: one trains a transformer via an auto-regressive paradigm, and the other adopts a two-stage scheme connecting…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Shihao Zhao , Yitong Chen , Zeyinzi Jiang , Bojia Zi , Shaozhe Hao , Yu Liu , Chaojie Mao , Kwan-Yee K. Wong

Simultaneous machine translation (SiMT) outputs translation while reading the source sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT methods adopt the prefix-to-prefix (prefix2prefix) training, where the…

Computation and Language · Computer Science 2024-05-29 Shoutao Guo , Shaolei Zhang , Yang Feng

Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider…

Computer Vision and Pattern Recognition · Computer Science 2021-06-28 Zhipeng Bao , Martial Hebert , Yu-Xiong Wang

Recently, diffusion models have emerged as a new paradigm for generative models. Despite the success in domains using continuous signals such as vision and audio, adapting diffusion models to natural language is under-explored due to the…

Computation and Language · Computer Science 2023-02-15 Shansan Gong , Mukai Li , Jiangtao Feng , Zhiyong Wu , Lingpeng Kong

Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication. Beyond accomplishing translation…

Computation and Language · Computer Science 2024-06-06 Shaolei Zhang , Qingkai Fang , Shoutao Guo , Zhengrui Ma , Min Zhang , Yang Feng

Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-annotated transcripts and translations. However, the…

Computation and Language · Computer Science 2024-10-28 Peter Polák , Ondřej Bojar

Sequence to sequence (SEQ2SEQ) models often lack diversity in their generated translations. This can be attributed to the limitation of SEQ2SEQ models in capturing lexical and syntactic variations in a parallel corpus resulting from…

Computation and Language · Computer Science 2018-10-18 Xuanli He , Gholamreza Haffari , Mohammad Norouzi

Keyphrases, that concisely summarize the high-level topics discussed in a document, can be categorized into present keyphrase which explicitly appears in the source text, and absent keyphrase which does not match any contiguous subsequence…

Computation and Language · Computer Science 2021-10-14 Jing Zhao , Junwei Bao , Yifan Wang , Youzheng Wu , Xiaodong He , Bowen Zhou

Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models, a popular choice for set…

Computation and Language · Computer Science 2022-10-25 Aman Madaan , Dheeraj Rajagopal , Niket Tandon , Yiming Yang , Antoine Bosselut

In this paper, we address the task of semantic-guided scene generation. One open challenge in scene generation is the difficulty of the generation of small objects and detailed local texture, which has been widely observed in global…

Computer Vision and Pattern Recognition · Computer Science 2020-04-01 Hao Tang , Dan Xu , Yan Yan , Philip H. S. Torr , Nicu Sebe