检索结果-内蒙古大学图书馆

Interspeech Conference

作者： Tuske, Zoltan Saon, George Kingsbury, Brian IBM Res AI Yorktown Hts NY 10598 USA

ISBN: (纸本)9781713836902

In our previous work we demonstrated that a single headed attention encoder-decoder model is able to reach state-of-the-art results in conversational speech recognition. In this paper, we further improve the results for both Switchboard 300 and 2000. Through use of an improved optimizer, speaker vector embeddings, and alternative speech representations we reduce the recognition errors of our LSTM system on Switchboard-300 by 4% relative. Compensation of the decoder model with the probability ratio approach allows more efficient integration of an external language model, and we report 5.9% and 11.5% WER on the SWB and CHM parts of Hub5'00 with very simple LSTM models. Our study also considers the recently proposed conformer, and more advanced self-attention based language models. Overall, the conformer shows similar performance to the LSTM;nevertheless, their combination and decoding with an improved LM reaches a new record on Switchboard-300, 5.0% and 10.0% WER on SWB and CHM. Our findings are also confirmed on Switchboard-2000, and a new state of the art is reported, practically reaching the limit of the benchmark.

关键词： encoder-decoder attention speech recognition AdamW Switchboard i-vector

来源：评论

学校读者我要写书评

暂无评论

Reducing Streaming ASR Model Delay with Self Alignment 22

Reducing Streaming ASR Model Delay with Self Alignment

引用

Interspeech Conference

作者： Kim, Jaeyoung Lu, Han Tripathi, Anshuman Zhang, Qian Sak, Hasim Google Inc Mountain View CA 94043 USA

ISBN: (纸本)9781713836902

Reducing prediction delay for streaming end-to-end ASR models with minimal performance regression is a challenging problem. Constrained alignment is a well-known existing approach that penalizes predicted word boundaries using external low-latency acoustic models. On the contrary, recently proposed FastEmit is a sequence-level delay regularization scheme encouraging vocabulary tokens over blanks without any reference alignments. Although all these schemes are successful in reducing delay, ASR word error rate (WER) often severely degrades after applying these delay constraining schemes. In this paper, we propose a novel delay constraining method, named self alignment. Self alignment does not require external alignment models. Instead, it utilizes Viterbi forced-alignments from the trained model to find the lower latency alignment direction. From LibriSpeech evaluation, self alignment outperformed existing schemes: 25% and 56% less delay compared to FastEmit and constrained alignment at the similar word error rate. For Voice Search evaluation, 12% and 25% delay reductions were achieved compared to FastEmit and constrained alignment with more than 2% WER improvements.

关键词： Transformer RNN-T sequence-to-sequence encoder-decoder end-to-end speech recognition

来源：评论

学校读者我要写书评

暂无评论

Investigating Recurrent Neural Networks for Diacritizing Arabic Text and Correcting Soft Spelling Mistakes

Investigating Recurrent Neural Networks for Diacritizing Ara...

引用

IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT)

作者： Almajdoubah, Ahmad N. Abandah, Gheith A. Suyyagh, Ashraf E. Univ Jordan Comp Engn Dept Amman Jordan

ISBN: (纸本)9781665442930

Modern Arabic language processing research aims to find efficient solutions to important problems such as adding diacritics to undiacritized text and correcting spelling mistakes. Some previous machine learning solutions solve these problems as one-to-one sequence transcription problems, which imposes restrictions on the type of errors that can be corrected. This work investigates transformer and encoder-decoder recurrent neural network models taking these two problems as case studies. These models solve sequence to sequence transcription problems without restrictions on the input and output lengths. We investigated several alternatives and evaluated them on two benchmark datasets. We recommend an encoder-decoder model that provides excellent accuracy. The encoder part has an embedding layer and a long short-term memory (LSTM) layer. The decoder part has an embedding layer, an LSTM layer, Luong attention between the two parts, and a dense output layer with softmax activation.

关键词： encoder-decoder recurrent neural network attention sequence-to-sequence Arabic diacritization spelling mistakes

来源：评论

学校读者我要写书评

暂无评论

Gazetteer-Guided Keyphrase Generation from Research Papers 1

引用

25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)

作者： Santosh, T. Y. S. S. Sanyal, Debarshi Kumar Bhowmick, Plaban Kumar Das, Partha Pratim IIT Kharagpur Dept Comp Sci & Engn Kharagpur W Bengal India Indian Assoc Cultivat Sci Kolkata India IIT Kharagpur GS Sanyal Sch Telecommun Kharagpur W Bengal India

ISBN: (数字)9783030757625

ISBN: (纸本)9783030757625;9783030757618

The task of keyphrase generation aims to generate the key phrases that capture the primary content of a document. An external domain-specific gazetteer can assist in generating keyphrases that are literally absent in the document (i.e., do not match any contiguous sub-sequence of source text) but relevant to the content of the document. In this paper, we present a technique to integrate knowledge from a gazetteer in order to improve keyphrase generation from research papers. We also present a copy mechanism that helps our model to utilize the gazetteer vocabulary to deal with the out-of-vocabulary words in keyphrases. Since constructing and maintaining relevant high-quality gazetteer by hand is very expensive, we also propose a method for automatic construction of a gazetteer given the input document, by leveraging similar documents in the training corpus. The thus constructed gazetteer helps focus on corpus-level information carried by other similar documents. Although this external information is crucial, it is never considered in previous studies. Experiments on real world datasets of research papers demonstrate that our proposed approach improves the performance of the state-of-the-art keyphrase generation models.

关键词： Gazetteer Keyphrase generation encoder-decoder Copy mechanism Attention

来源：评论

学校读者我要写书评

暂无评论

DEANet: Dual encoder with Attention Network for Semantic Segmentation of Remote Sensing Imagery

引用

REMOTE SENSING 2021年第19期13卷 3900-3900页

作者： Wei, Haoran Xu, Xiangyang Ou, Ni Zhang, Xinru Dai, Yaping Beijing Inst Technol State Key Lab Intelligent Control & Decis Complex Beijing 100081 Peoples R China Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China

Remote sensing has now been widely used in various fields, and the research on the automatic land-cover segmentation methods of remote sensing imagery is significant to the development of remote sensing technology. Deep learning methods, which are developing rapidly in the field of semantic segmentation, have been widely applied to remote sensing imagery segmentation. In this work, a novel deep learning network-Dual encoder with Attention Network (DEANet) is proposed. In this network, a dual-branch encoder structure, whose first branch is used to generate a rough guidance feature map as area attention to help re-encode feature maps in the next branch, is proposed to improve the encoding ability of the network, and an improved pyramid partial decoder (PPD) based on the parallel partial decoder is put forward to make fuller use of the features form the encoder along with the receptive filed block (RFB). In addition, an edge attention module using the transfer learning method is introduced to explicitly advance the segmentation performance in edge areas. Except for structure, a loss function composed with the weighted Cross Entropy (CE) loss and weighted Union subtract Intersection (UsI) loss is designed for training, where UsI loss represents a new region-based aware loss which replaces the IoU loss to adapt to multi-classification tasks. Furthermore, a detailed training strategy for the network is introduced as well. Extensive experiments on three public datasets verify the effectiveness of each proposed module in our framework and demonstrate that our method achieves more excellent performance over some state-of-the-art methods.

关键词： remote sensing land cover classification deep learning semantic segmentation encoder-decoder attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Enhanced Recognition of Offline Marathi Handwriting via a Self-Additive Attention Mechanism

引用

TRAITEMENT DU SIGNAL 2023年第6期40卷 2853-2860页

作者： Chikmurge, Diptee Vishwanath Raghunathan, Shriram VIT Bhopal Univ Sch Comp Sci & Engn Bhopal 466114 Madhya Pradesh India MIT Acad Engn Sch Comp Engn Alandi 412105 Maharashtra India

Background: Offline Marathi handwriting recognition presents a significant challenge due to the script's complexity and the variability of individual writing styles. Methods: In the present work, an advanced encoder-decoder framework is introduced, wherein a novel self -additive-attention mechanism is integrated. This model capitalizes on a Convolutional Neural Network paired with a Joint Scale Feature Extractor (CNN-JSE) to discern low-level image features within the IIIT-HW-Dev dataset. Such features are subsequently fed into an encoder model that employs a dual-phase fusion process: initially leveraging a Bidirectional Long Short-Term Memory (BiLSTM) network, followed by the self-additive-attention mechanism to maintain dependencies over extensive sequences. Results: The fusion output, comprising BiLSTM and self-additive attention data, is conveyed to a Connectionist Temporal Classifier (CTC) decoder. This decoder adeptly identifies character sequences within Marathi words. The introduction of self-additive attention alongside BiLSTM is instrumental in preserving dependencies that are both long-range and multi-stage. Performance Evaluation: The efficacy of the proposed system was rigorously evaluated on the multi-author IIIT-HW-Dev dataset. Performance metrics, specifically Character Error Rate (CER) and Word Error Rate (WER), were employed for benchmarking against various established models. Conclusion: The proposed methodology demonstrates a significant enhancement in the recognition of handwritten Marathi text, thus facilitating the conversion of handwritten documents into machine-editable text. The utilization of self -additive attention within the BiLSTM framework underscores its potential in capturing complex dependencies, setting a new precedent in automated handwriting recognition technologies. Significance: This study not only paves the way for increased accuracy in handwritten text recognition but also contributes a novel approach to the encoding of fea

关键词： optical character recognition bidirectional long short-term memory convolutional neural network encoder-decoder and connectionist temporal classifier

来源：评论

学校读者我要写书评

暂无评论

The Impact of Text Generation Techniques on Neural Image Captioning: An Empirical Study

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第10期14卷 1080-1090页

作者： Ding, Linna Jiang, Mingyue Nie, Liming Qing, Zuzhang Ding, Zuohua Zhejiang Sci Tech Univ Fac Comp Sci & Technol Hangzhou Zhejiang Peoples R China Nanyang Technol Univ Sch Comp Sci & Technol Singapore Singapore Zhejiang Petr Integrated Energy Sales Co Ltd Hangzhou Zhejiang Peoples R China

Image captioning is an advanced NLP task that has various practical applications. To meet the requirement of visual information understanding and textual information generation, the encoder-decoder framework has been widely adopted by image captioning models. In this context, the encoder is responsible for transforming an image into vector representation, and the decoder acts as a text generator for yielding an image caption. It is obvious and intuitive that the decoder is crucial for the entire image captioning model. However, there is a lack of comprehensive studies in which the impact of various aspects of the decoder on the image captioning is investigated. To advance the understanding of the impacts of text generation techniques employed by the decoder, we conduct an extensive empirical analysis of three types of language models, two types of decoding strategies and two types of training methods, based on four stateof-the-art image captioning models. Our experimental results demonstrate that the language model affects the performance of image captioning models, while different language models may benefit different image captioning models. In addition, it is also revealed that among the decoding and training strategies under investigation, the beam search, AOA mechanism and the reinforcement learning based training method can generally improve the performance of image captioning models. Moreover, the results also show that the combinational usage of these strategies always outperforms the use of single strategy for the task of image captioning.

关键词： Image captioning encoder-decoder text generation techniques

来源：评论

学校读者我要写书评

暂无评论

Absolute Phase Unwrapping with Deep Neural Network for Structured Light 3D Reconstruction 33

Absolute Phase Unwrapping with Deep Neural Network for Struc...

引用

33rd Chinese Control and Decision Conference (CCDC)

作者： Chang, Wan Xiang, Sen Deng, Huiping Wu, Jin Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan 430081 Peoples R China Minist Educ Engn Res Ctr Met Auto & Measurement Tech Wuhan 430081 Peoples R China

ISBN: (纸本)9781665440899

Phase-coding structured light is an important technique in 3D reconstruction, However, a great challenge is the wrapped phase that causes geometry ambiguity, Conventional unwrapping methods such as spatial and temporal approaches face the problem of error propagation and low efficiency, In this paper, we propose to solve the phase unwrapping problem with a deep neural network To be specific, the phase unwrapping problem is cast to a semantic segmentation task, where the wrapped phase is the input and the fringe index for every pixel is the output An encoder-decoder architecture, which is like U-net, is adopted as the network We further propose a combined loss function by considering cross entropy loss, phase consistency loss and edge consistency loss, With 1 0000 artificially synthesized samples, the proposed method converges welL Experimental results demonstrate that the trained model well predicts fringe orders on both simulation data and real captured data, In addition, it unwrapps every pixel independently and avoids phase error propagation, and further achieves accurate 3D reconstruction,

关键词： 3D Reconstruction Phase Unwrapping Deep Neural Network encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

MRD: A Memory Relation decoder for Online Handwritten Mathematical Expression Recognition 16th

MRD: A Memory Relation Decoder for Online Handwritten Mathem...

引用

16th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Wang, Jiaming Wang, Qing Du, Jun Zhang, Jianshu Wang, Bin Ren, Bo Univ Sci & Technol China Hefei Anhui Peoples R China Guangdong Artificial Intelligence & Digital Econ Pazhou Lab Guangzhou Peoples R China Tencent Youtu Lab Hefei Anhui Peoples R China

ISBN: (纸本)9783030863340;9783030863333

Recently, attention based encoder-decoder methods have been widely used in online handwritten mathematical expression recognition, which achieve significant improvements compared to traditional methods. The encoder-decoder methods usually employ string decoders to generate the recognition result, which are not well matched for tree-structured languages like math expression. A novel sequential relation decoder (SRD) was introduced to recognize the online mathematical expression as a math tree, which can be decomposed into a subtree sequence and each subtree consists of a relation node and two symbol nodes (related symbol node and primary symbol node). However, the alignments between these two symbol nodes were implemented by spatial attention probabilities, leading to incorrect recognition if spatial attention is not accurate. In this paper, we propose a memory relation decoder (MRD), equipped with a memory based attention model to determine the correspondence between two symbol nodes. Specifically, at each decoding step, this memory based attention finds the corresponding primary symbol node in the memory and treats it as the related symbol node, which actually achieves the alignments between two symbol nodes in an explicit manner. Besides, we propose to introduce global visual information while calculating attention probabilities to help alleviate the ambiguous problems in online handwritten mathematical expression recognition. Evaluated on a benchmark published by CROHME competition, the proposed approach can substantially outperform previous encoder-decoder methods.

关键词： Handwritten mathematical expression recognition encoder-decoder Tree structure Memory based attention

来源：评论

学校读者我要写书评

暂无评论

Optimized Object Detection Method for FPGA Implementation 6

Optimized Object Detection Method for FPGA Implementation

引用

6th International Conference on Wireless Communications, Signal Processing and Networking (IEEE WiSPNET)

作者： Babu, Praveenkumar Parthasarathy, Eswaran SRM Inst Sci & Technol SRM Nagar Dept Elect & Commun Engn Chennai 603203 Tamil Nadu India

ISBN: (纸本)9781665440868

Technological advancements are growing faster and better. Real-time object detection is still a challenging task in computer vision and image processing algorithms. For this purpose, hardware platforms like Field-Programmable Gate Arrays(FPGAs) play a significant role in the implementation of object detection algorithms. This paper proposes an optimized YOLOv4 object detection algorithm for FPGA implementation. The proposed method involves in the addition of encoder-decoder network followed by Feature Pyramid Network(FPN) in YOLOv4 architecture. This proposed method achieves better accuracy and performance with mean Average Precision (mAP) of 56.7 and 72.58 billion floating-point operations per second (BFLOPs) respectively at nearly 65 fps on MS-COCO benchmark dataset. The results prove that suggested method is favourable for the hardware implementation on comparing with other detection algorithms.

关键词： object detection FPGA YOLOv4 algorithm encoder-decoder FPN

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：