检索结果-内蒙古大学图书馆

Interspeech Conference

作者： Wu, Minglin Li, Kun Leung, Wai-Kim Meng, Helen Chinese Univ Hong Kong Dept Syst Engn & Engn Management Human Comp Commun Lab Hong Kong Peoples R China SpeechX Ltd Hong Kong Peoples R China Ctr Perceptual & Interact Intelligence CPII Ltd Hong Kong Peoples R China

ISBN: (纸本)9781713836902

This paper introduces two Transformer-based architectures for Mispronunciation Detection and Diagnosis (MDD). The first Transformer architecture (T-1) is a standard setup with an encoder, a decoder, a projection part and the Cross Entropy (CE) loss. T-1 takes in Mel-Frequency Cepstral Coefficients (MFCC) as input. The second architecture (T-2) is based on wav2vec 2.0, a pretraining framework. T-2 is composed of a CNN feature encoder, several Transformer blocks capturing contextual speech representations, a projection part and the Connectionist Temporal Classification (CTC) loss. Unlike T-1, T-2 takes in raw audio data as input. Both models are trained in an end-to-end manner. Experiments are conducted on the CU-CHLOE corpus, where T-1 achieves a Phone Error Rate (PER) of 8.69% and F-measure of 77.23%;and T-2 achieves a PER of 5.97% and F-measure of 80.98 %. Both models significantly outperform the previously proposed AGPM and CNN-RNN-CTC models, with PERs at 11.1% and 12.1% respectively, and F-measures at 72.61% and 74.65 % respectively.

关键词： Mispronunciation Detection and Diagnosis (MDD) Transformer encoder-decoder wav2vec 2.0 CNN feature encoder

来源：评论

学校读者我要写书评

暂无评论

Short-Term Traffic Forecasting using LSTM-based Deep Learning Models 7

Short-Term Traffic Forecasting using LSTM-based Deep Learnin...

引用

Moratuwa Engineering Research Conference (MERCon) / 7th International Multidisciplinary Engineering Research Conference

作者： Haputhanthri, Dilantha Wijayasiri, Adeesha Univ Moratuwa Dept Comp Sci & Engn Moratuwa Sri Lanka

ISBN: (纸本)9781665437530

Accurate short-term traffic volume forecasting has become a component with growing importance in traffic management in intelligent transportation systems (ITS). A significant amount of related works on short-term traffic forecasting has been proposed based on traditional learning approaches, and deep learning-based approaches have also made significant strides in recent years. In this paper, we explore several deep learning models that are based on long-short term memory (LSTM) networks to automatically extract inherent features of traffic volume data for forecasting. A simple LSTM model, LSTM encoder-decoder model, CNN-LSTM model and a Conv-LSTM model were designed and evaluated using a real-world traffic volume dataset for multiple prediction horizons. Finally, the experimental results are analyzed, and the Conv-LSTM model produced the best performance with a MAPE of 9.03% for the prediction horizon of 15 minutes. Also, the paper discusses the behavior of the models with the traffic volume anomalies due to the Covid-19 pandemic.

关键词： CNN-LSTM Conv-LSTM encoder-decoder LSTM traffic volume forecasting

来源：评论

学校读者我要写书评

暂无评论

Attention-Based End-to-End Named Entity Recognition from Speech 24th

Attention-Based End-to-End Named Entity Recognition from Spe...

引用

24th Annual International Conference on Text, Speech, and Dialogue (TSD)

作者： Porjazovski, Dejan Leinonen, Juho Kurimo, Mikko Aalto Univ Dept Signal Proc & Acoust Espoo Finland

ISBN: (纸本)9783030835262;9783030835279

Named entities are heavily used in the field of spoken language understanding, which uses speech as an input. The standard way of doing named entity recognition from speech involves a pipeline of two systems, where first the automatic speech recognition system generates the transcripts, and then the named entity recognition system produces the named entity tags from the transcripts. In such cases, automatic speech recognition and named entity recognition systems are trained independently, resulting in the automatic speech recognition branch not being optimized for named entity recognition and vice versa. In this paper, we propose two attention-based approaches for extracting named entities from speech in an end-to-end manner, that show promising results. We compare both attention-based approaches on Finnish, Swedish, and English data sets, underlining their strengths and weaknesses.

关键词： Named entity recognition Automatic speech recognition End-to-end encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

A Novel CNN-based Model for Medical Image Registration

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第11期14卷 1125-1136页

作者： Gao, Hui Liang, Mingliang Zhengzhou Railway Vocat & Tech Coll Zhengzhou 451460 Henan Peoples R China

The registration of the deformable image is applied widely to image diagnosis, the monitoring of the disease, and the navigation of the surgery with the aim of learning the correspondence of the anatomist among an image of motion and an image of static. The procedure of the registration of an image mainly includes three steps: the creation of a model of the deformation, a function design for the mensuration of the similarity, and the step of learning for the optimization of the parameter. In the current article, 2-stream architecture is designed, which has the ability to sequentially estimate the fields of the registration of the multi-level by a couple of the pyramids of the feature. In this paper, a 3D network of the encoder decoder with the 2-stream is designed, which calculates 2 pyramids of the feature of the convolutional as separately by 2 volumes of the input. Also, the registration of the pyramid of the sequential is proposed, which in it, a trail of the modules of the pyramid registration (PR) for the prediction of the fields of the registration of the multi-level is designed as straight by the pyramids of the feature of the decoding. In addition, the modules of PR can be augmented with the computation of the 3D correlations of the local among the pyramids of the feature, which this work leads to the further improvement of the presented approach. Thus, it is capable of collecting the detailed anatomical structure of the brain. The proposed method is tested in three criterion datasets about the registration of MRI of the brain. The evaluation outcomes display that the presented approach outperforms the advanced approaches with a big value.

关键词： Image registration convolutional neural network Pyramid Registration (PR) encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Long-sequence voltage series forecasting for internal short circuit early detection of lithium-ion batteries

引用

PATTERNS 2023年第6期4卷 100732页

作者： Cui, Binghan Wang, Han Li, Renlong Xiang, Lizhi Du, Jiannan Zhao, Huaian Li, Sai Zhao, Xinyue Yin, Geping Cheng, Xinqun Ma, Yulin Huo, Hua Zuo, Pengjian Han, Guokang Du, Chunyu Harbin Inst Technol Sch Chem & Chem Engn MIIT Key Lab Crit Mat Technol New Energy Convers & Harbin 150001 Peoples R China

Accurate early detection of internal short circuits (ISCs) is indispensable for safe and reliable application of lithium-ion batteries (LiBs). However, the major challenge is finding a reliable standard to judge whether the battery suffers from ISCs. In this work, a deep learning approach with multi-head attention and a multi-scale hierarchical learning mechanism based on encoder-decoder architecture is developed to accurately forecast voltage and power series. By using the predicted voltage without ISCs as the standard and detecting the consistency of the collected and predicted voltage series, we develop a method to detect ISCs quickly and accurately. In this way, we achieve an average percentage accuracy of 86% on the dataset, including different batteries and the equivalent ISC resistance from 1,000 U to 10 U, indicating successful application of the ISC detection method.

关键词： lithium-ion battery internal short circuit detection voltage prediction power prediction time-series forecasting deep learning encoder-decoder attention model

来源：评论

学校读者我要写书评

暂无评论

ResneSt-Transformer: Joint attention segmentation-free for end-to-end handwriting paragraph recognition model

引用

ARRAY 2023年 19卷

作者： Hamdan, Mohammed Cheriet, Mohamed Univ Quebec ETS Synchromedia Lab Syst Engn 1100 Notre Dame St W Montreal PQ H3C 1K3 Canada

Offline handwritten text recognition (HTR) typically relies on segmented text-line images for training and transcription. However, acquiring line-level position and transcript information can be challenging and time-consuming, while automatic line segmentation algorithms are prone to errors that impede the recognition phase. To address these issues, we introduce a state-of-the-art solution that integrates vision and language models using efficient split and multi-head attention neural networks, referred to as joint attention (ResneSt-Transformer), for end-to-end recognition of handwritten paragraphs. Our proposed novel one-stage, segmentation-free pipeline employs joint attention mechanisms to process paragraph images in an end-to-end trainable manner. This pipeline comprises three modules, with the output of one serving as the input for the next. Initially, a feature extraction module employing a CNN with a split attention mechanism (ResneSt50) is utilized. Subsequently, we develop an encoder module containing four transformer layers to generate robust representations of the entire paragraph image. Lastly, we designed a decoder module with six transformer layers to construct weighted masks. The encoder and decoder modules incorporate a multi-head self-attention mechanism and positional encoding, enabling the model to concentrate on specific feature maps at the current time step. By leveraging joint attention and a segmentation-free approach, our neural network calculates split attention weights on the visual representation, facilitating implicit line segmentation. This strategy signifies a substantial advancement toward achieving end-to-end transcription of entire paragraphs. Experiments conducted on paragraph-level benchmark datasets, including RIMES, IAM, and READ 2016 test datasets, demonstrate competitive results compared to recent paragraph-level models while maintaining reduced complexity. The code and pre-trained models are available on our GitHub repository

关键词： Handwritten text recognition ResneSt Transformer Self attention Segmentation-free Lexicon-free Paragraph transcription OCR encoder-decoder Image-seq

来源：评论

学校读者我要写书评

暂无评论

Low-dose CT image denoising method based on generative adversarial network

引用

Journal of Measurement Science and Instrumentation 2024年第4期15卷 490-498页

作者： JIAO Fengyuan YANG Zhixiu SHI Shaojie CAO Weiguo Shanxi Provincial Key Laboratory for Biomedical Imaging and Big Data North University of ChinaTaiyuan 030051China School of Information and Communication Engineering North University of ChinaTaiyuan 030051China School of Environment and Safety Engineering North University of ChinaTaiyuan 030051China

In order to solve the problems of artifacts and noise in low-dose computed tomography(CT)images in clinical medical diagnosis,an improved image denoising algorithm under the architecture of generative adversarial network(GAN)was ***,a noise model based on style GAN2 was constructed to estimate the real noise distribution,and the noise information similar to the real noise distribution was generated as the experimental noise data ***,a network model with encoder-decoder architecture as the core based on GAN idea was constructed,and the network model was trained with the generated noise data set until it reached the optimal ***,the noise and artifacts in low-dose CT images could be removed by inputting low-dose CT images into the denoising *** experimental results showed that the constructed network model based on GAN architecture improved the utilization rate of noise feature information and the stability of network training,removed image noise and artifacts,and reconstructed image with rich texture and realistic visual effect.

关键词： low-dose CT image generative adversarial network noise and artifacts encoder-decoder atrous spatial pyramid pooling(ASPP)

来源：评论

学校读者我要写书评

暂无评论

Mixed Diagnostics for Longitudinal Properties of Electron Bunches in a Free-Electron Laser

引用

FRONTIERS IN PHYSICS 2022年 10卷

作者： Zhu, J. Lockmann, N. M. Czwalinna, M. K. Schlarb, H. Deutsch Elektronen Synchrotron DESY Hamburg Germany

Longitudinal properties of electron bunches are critical for the performance of a wide range of scientific facilities. In a free-electron laser, for example, the existing diagnostics only provide very limited longitudinal information of the electron bunch during online tuning and optimization. We leverage the power of artificial intelligence to build a neural network model using experimental data, in order to bring the destructive longitudinal phase space (LPS) diagnostics online virtually and improve the existing current profile online diagnostics which uses a coherent transition radiation (CTR) spectrometer. The model can also serve as a digital twin of the real machine on which algorithms can be tested efficiently and effectively. We demonstrate at the FLASH facility that the encoder-decoder model with more than one decoder can make highly accurate predictions of megapixel LPS images and coherent transition radiation spectra concurrently for electron bunches in a bunch train with broad ranges of LPS shapes and peak currents, which are obtained by scanning all the major control knobs for LPS manipulation. Furthermore, we propose a way to significantly improve the CTR spectrometer online measurement by combining the predicted and measured spectra. Our work showcases how to combine virtual and real diagnostics in order to provide heterogeneous and reliable mixed diagnostics for scientific facilities.

关键词： free-electron laser (FEL) longitudinal phase space machine learning encoder-decoder mixed diagnostics

来源：评论

学校读者我要写书评

暂无评论

"More Than Deep Learning": post-processing for API sequence recommendation

引用

EMPIRICAL SOFTWARE ENGINEERING 2022年第1期27卷 15-15页

作者： Chen, Chi Peng, Xin Chen, Bihuan Sun, Jun Xing, Zhenchang Wang, Xin Zhao, Wenyun Fudan Univ Sch Comp Sci Shanghai Peoples R China Fudan Univ Shanghai Key Lab Data Sci Shanghai Peoples R China Singapore Management Univ Singapore Singapore Australian Natl Univ Canberra ACT Australia

In the daily development process, developers often need assistance in finding a sequence of APIs to accomplish their development tasks. Existing deep learning models, which have recently been developed for recommending one single API, can be adapted by using encoder-decoder models together with beam search to generate API sequence recommendations. However, the generated API sequence recommendations heavily rely on the probabilities of API suggestions at each decoding step, which do not take into account other domain-specific factors (e.g., whether an API suggestion satisfies the program syntax and how diverse the API sequence recommendations are). Moreover, it is difficult for developers to find similar API sequence recommendations, distinguish different API sequence recommendations, and make a selection when the API sequence recommendations are ordered by probabilities. Thus, what we need is more than deep learning. In this paper, we propose an approach, named Cook, to combine deep learning models with post-processing strategies for API sequence recommendation. Specifically, we enhance beam search with code-specific heuristics to improve the quality of API sequence recommendations. We develop a clustering algorithm to cluster API sequence recommendations so as to make it easier for developers to find similar API sequence recommendations and distinguish different API sequence recommendations. We also propose a method to generate a summary for each cluster to help developers understand the API sequence recommendations. Our evaluation results have shown that (1) three deep learning models with our heuristic-enhanced beam search achieved better performance than with the original beam search in terms of CIDEr-1, CIDEr-5 and CIDEr-10 scores, with an average improvement of 1.8, 2.3 and 2.3, respectively;and (2) our clustering algorithm achieved high performance on six metrics and outperformed two variant clustering algorithms. Moreover, our user study with 24 participants

关键词： API Recommendation Deep learning encoder-decoder Post-processing

来源：评论

学校读者我要写书评

暂无评论

Robust Shadow Detection by Exploring Effective Shadow Contexts 21

Robust Shadow Detection by Exploring Effective Shadow Contex...

引用

29th ACM International Conference on Multimedia (MM)

作者： Fang, Xianyong He, Xiaohao Wang, Linbo Shen, Jianbing Anhui Univ Hefei Peoples R China Univ Macau Macau Peoples R China

ISBN: (纸本)9781450386517

Effective contexts for separating shadows from non-shadow objects can appear in different scales due to different object sizes. This paper introduces a new module, Effective-Context Augmentation (ECA), to utilize these contexts for robust shadow detection with deep structures. Taking regular deep features as global references, ECA enhances the discriminative features from the parallelly computed fine-scale features and, therefore, obtains robust features embedded with effective object contexts by boosting them. We further propose a novel encoder-decoder style of shadow detection method where ECA acts as the main building block of the encoder to extract strong feature representations and the guidance to the classification process of the decoder. Moreover, the networks are optimized with only one loss, which is easy to train and does not have the instability caused by extra losses superimposed on the intermediate features among existing popular studies. Experimental results show that the proposed method can effectively eliminate fake ***, our method outperforms state-of-the-arts methods and improves over 13.97% and 34.67% on the challenging SBU and UCF datasets respectively in balance error rate.

关键词： Shadow detection deep learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：