English
Related papers

Related papers: Unimodal Aggregation for CTC-based Speech Recognit…

200 papers

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Lijie Fan , Luming Tang , Siyang Qin , Tianhong Li , Xuan Yang , Siyuan Qiao , Andreas Steiner , Chen Sun , Yuanzhen Li , Tao Zhu , Michael Rubinstein , Michalis Raptis , Deqing Sun , Radu Soricut

This paper integrates a voice activity detection (VAD) function with end-to-end automatic speech recognition toward an online speech interface and transcribing very long audio recordings. We focus on connectionist temporal classification…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-16 Takenori Yoshimura , Tomoki Hayashi , Kazuya Takeda , Shinji Watanabe

Video-based person re-identification (ReID) is challenging due to the presence of various interferences in video frames. Recent approaches handle this problem using temporal aggregation strategies. In this work, we propose a novel Context…

Computer Vision and Pattern Recognition · Computer Science 2022-07-07 Kan Wang , Changxing Ding , Jianxin Pang , Xiangmin Xu

The gap between speech and text modalities is a major challenge in speech-to-text translation (ST). Different methods have been proposed to reduce this gap, but most of them require architectural changes in ST training. In this work, we…

Computation and Language · Computer Science 2023-06-06 Phuong-Hang Le , Hongyu Gong , Changhan Wang , Juan Pino , Benjamin Lecouteux , Didier Schwab

Universal domain adaptation (UniDA) aims to transfer knowledge from the source domain to the target domain without any prior knowledge about the label set. The challenge lies in how to determine whether the target samples belong to common…

Computer Vision and Pattern Recognition · Computer Science 2023-08-31 Didi Zhu , Yincuan Li , Junkun Yuan , Zexi Li , Kun Kuang , Chao Wu

Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition models. Both models define a transcription probability by…

Computation and Language · Computer Science 2017-06-07 Liang Lu , Lingpeng Kong , Chris Dyer , Noah A. Smith

In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-04 Thai-Son Nguyen , Sebastian Stueker , Alex Waibel

Multimodalities provide promising performance than unimodality in most tasks. However, learning the semantic of the representations from multimodalities efficiently is extremely challenging. To tackle this, we propose the Transformer based…

Computer Vision and Pattern Recognition · Computer Science 2019-11-14 Wubo Li , Wei Zou , Xiangang Li

We study the joint learning of image-to-text and text-to-image generations, which are naturally bi-directional tasks. Typical existing works design two separate task-specific models for each task, which impose expensive design efforts. In…

Computer Vision and Pattern Recognition · Computer Science 2021-10-20 Yupan Huang , Hongwei Xue , Bei Liu , Yutong Lu

Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods. Although these two representations have recently demonstrated their excellent performance, they still have apparent…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Rui Peng , Rongjie Wang , Zhenyu Wang , Yawen Lai , Ronggang Wang

Multimodal models have achieved remarkable success in natural image segmentation, yet they often underperform when applied to the medical domain. Through extensive study, we attribute this performance gap to the challenges of multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-09-11 Wenjun Yu , Yinchen Zhou , Jia-Xuan Jiang , Shubin Zeng , Yuee Li , Zhong Wang

The acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion is a natural end-to-end (E2E) system directly targeting word as output unit. Two issues exist in the system: first, the current output of the CTC…

Computation and Language · Computer Science 2019-09-06 Amit Das , Jinyu Li , Guoli Ye , Rui Zhao , Yifan Gong

Joint modeling of language and vision has been drawing increasing interest. A multimodal data representation allowing for bidirectional retrieval of images by sentences and vice versa is a key aspect. In this paper we present three…

Machine Learning · Computer Science 2016-12-07 Youssef Mroueh , Etienne Marcheret , Vaibhava Goel

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Machine Learning · Computer Science 2025-10-13 T. Ed Li , Junyu Ren

We propose a unified representation learning framework to address the Cross Model Compatibility (CMC) problem in the context of visual search applications. Cross compatibility between different embedding models enables the visual search…

Computer Vision and Pattern Recognition · Computer Science 2020-08-12 Chien-Yi Wang , Ya-Liang Chang , Shang-Ta Yang , Dong Chen , Shang-Hong Lai

Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP align…

Computation and Language · Computer Science 2025-10-20 Qiyu Wu , Shuyang Cui , Satoshi Hayakawa , Wei-Yao Wang , Hiromi Wakaki , Yuki Mitsufuji

Visual language models encounter challenges in computational efficiency and latency, primarily due to the substantial redundancy in the token representations of high-resolution images and videos. Current attention/similarity-based…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Dehua Zheng , Mouxiao Huang , Borui Jiang , Hailin Hu , Xinghao Chen

Finding relevant moments and highlights in videos according to natural language queries is a natural and highly valuable common need in the current video content explosion era. Nevertheless, jointly conducting moment retrieval and highlight…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Ye Liu , Siyuan Li , Yang Wu , Chang Wen Chen , Ying Shan , Xiaohu Qie

We propose a CTC alignment-based single step non-autoregressive transformer (CASS-NAT) for speech recognition. Specifically, the CTC alignment contains the information of (a) the number of tokens for decoder input, and (b) the time span of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-15 Ruchao Fan , Wei Chu , Peng Chang , Jing Xiao

Embedding text sequences is a widespread requirement in modern language understanding. Existing approaches focus largely on constant-size representations. This is problematic, as the amount of information contained in text often varies with…

Computation and Language · Computer Science 2023-10-04 Guanghui Qin , Benjamin Van Durme