English
Related papers

Related papers: Attention Enhanced Citrinet for Speech Recognition

200 papers

This paper introduces a novel method to diagnose the source-target attention in state-of-the-art end-to-end speech recognition models with joint connectionist temporal classification (CTC) and attention training. Our method is based on the…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-03 Nanxin Chen , Piotr Żelasko , Jesús Villalba , Najim Dehak

We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image classification, object detection and instance segmentation. By just replacing…

Computer Vision and Pattern Recognition · Computer Science 2021-08-04 Aravind Srinivas , Tsung-Yi Lin , Niki Parmar , Jonathon Shlens , Pieter Abbeel , Ashish Vaswani

The quadratic complexity of attention mechanisms poses a critical bottleneck for large language models processing long contexts. While dynamic sparse attention methods offer input-adaptive efficiency, they face fundamental trade-offs:…

Computation and Language · Computer Science 2026-02-06 Siran Liu , Guoxia Wang , Sa Wang , Jinle Zeng , HaoYang Xie , Siyu Lou , JiaBin Yang , DianHai Yu , Haifeng Wang , Chao Yang

This paper proposes an adaptation method for end-to-end speech recognition. In this method, multiple automatic speech recognition (ASR) 1-best hypotheses are integrated in the computation of the connectionist temporal classification (CTC)…

Computation and Language · Computer Science 2021-04-01 Cong-Thanh Do , Rama Doddipatla , Thomas Hain

CTR prediction has been widely used in the real world. Many methods model feature interaction to improve their performance. However, most methods only learn a fixed representation for each feature without considering the varying importance…

Information Retrieval · Computer Science 2022-12-02 Fangye Wang , Yingxu Wang , Dongsheng Li , Hansu Gu , Tun Lu , Peng Zhang , Ning Gu

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-22 Rui Wang , Zhihua Wei , Haoran Duan , Shouling Ji , Yang Long , Zhen Hong

Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Yi Zhang , Lingxiao Wei , Bowei Zhang , Ziwei Liu , Kai Yi , Shu Hu

With the success of deep learning methods in many image processing tasks, deep learning approaches have also been introduced to the phase retrieval problem recently. These approaches are different from the traditional iterative optimization…

Computer Vision and Pattern Recognition · Computer Science 2022-07-29 Qiuliang Ye , Li-Wen Wang , Daniel P. K. Lun

Visual attention mechanisms have proven to be integrally important constituent components of many modern deep neural architectures. They provide an efficient and effective way to utilize visual information selectively, which has shown to be…

Computer Vision and Pattern Recognition · Computer Science 2019-05-24 Siddhesh Khandelwal , Leonid Sigal

Automated fetal head segmentation in ultrasound images is critical for accurate biometric measurements in prenatal care. While existing deep learning approaches have achieved a reasonable performance, they struggle with issues like low…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Ammar Bhilwarawala , Mainak Bandyopadhyay

In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Simpenzwe Honore Leandre , Natenaile Asmamaw Shiferaw , Dillip Rout

A key challenge in continuous sign language recognition (CSLR) is to efficiently capture long-range spatial interactions over time from the video input. To address this challenge, we propose TCNet, a hybrid network that effectively models…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Hui Lu , Albert Ali Salah , Ronald Poppe

While self-attention mechanism has shown promising results for many vision tasks, it only considers the current features at a time. We show that such a manner cannot take full advantage of the attention mechanism. In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2020-07-13 Xu Ma , Jingda Guo , Sihai Tang , Zhinan Qiao , Qi Chen , Qing Yang , Song Fu

Recently, conformer-based end-to-end automatic speech recognition, which outperforms recurrent neural network based ones, has received much attention. Although the parallel computing of conformer is more efficient than recurrent neural…

Sound · Computer Science 2021-07-26 Shengqiang Li , Menglong Xu , Xiao-Lei Zhang

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

Sound · Computer Science 2022-07-05 Kun Wei , Pengcheng Guo , Ning Jiang

In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-17 Li Fu , Xiaoxiao Li , Libo Zi , Zhengchen Zhang , Youzheng Wu , Xiaodong He , Bowen Zhou

The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources,…

Computation and Language · Computer Science 2015-10-20 Yajie Miao , Mohammad Gowayyed , Florian Metze

We present an efficient speech separation neural network, ARFDCN, which combines dilated convolutions, multi-scale fusion (MSF), and channel attention to overcome the limited receptive field of convolution-based networks and the high…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-12 Junyu Wang

As one of the major branches of automatic speech recognition, attention-based models greatly improves the feature representation ability of the model. In particular, the multi-head mechanism is employed in the attention, hoping to learn…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-24 Kai Liu , Hailiang Xiong , Gangqiang Yang , Zhengfeng Du , Yewen Cao , Danyal Shah

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Sound · Computer Science 2019-07-03 Miquel India , Pooyan Safari , Javier Hernando