检索结果-内蒙古大学图书馆

A sequence-to-sequence Framework Based on Transformer With Masked Language Model for Optical Music Recognition

IEEE ACCESS 2022年 10卷 118243-118252页

作者： Wen, Cuihong Zhu, Longjiao Hunan Normal Univ Coll Informat Sci & Engn Changsha 410081 Peoples R China Peking Univ Coll Engn Dept Adv Mfg & Robot Beijing 100871 Peoples R China

Optical music recognition technology is of great significance in the development of the digital music. In recent years, the convolutional recurrent neural network framework with connectionist temporal classification has been used in music recognition. However, its loss function is calculated in serial mode, which leads to low efficiency in training and difficulty in convergence. Additionally, because of the gradient disappearance of excessive long music sequences, the existing music recognition models are hard to learn the relationships between musical symbols, resulting in high sequence error rate. Therefore, we propose a sequence-to-sequence framework based on transformer with masked language model to deal with these problems. The context representation between musical symbols can be captured further by the self-attention module in the transformer, which will reduce the sequence error rate. In addition, we refer to the masked language model and design a mask matrix to predict each musical symbol in a parallel way, so as to speed up the training process. Our experiments are carried out on the printed images of music stave dataset, and the results show that our proposed method is training-efficient and has great improvement in sequence accuracy rate.

关键词： Masked language model neural networks optical music recognition sequence-to-sequence transformer

来源：评论

学校读者我要写书评

暂无评论

sequence-to-sequence learning for link-scheduling in D2D communication networks

引用

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS 2023年第1期212卷

作者： Elsheikh, Ahmed Ibrahim, Ahmed S. Ismail, Mahmoud H. Cairo Univ Math & Engn Phys Dept Giza 12613 Egypt Florida Int Univ Dept Elect & Comp Engn Miami FL 33174 USA Amer Univ Sharjah Elect Engn Dept Sharjah 26666 U Arab Emirates Cairo Univ Elect & Commun Engn Dept Giza 12613 Egypt

Scheduling of Device-to-Device (D2D) links in communication networks conventionally relies on solving NP-hard combinatorial optimization problems. These types of solution approaches will not be suitable for the service requirements of future networks due to the associated computational complexity. That is why Deep Learning (DL) is one of the promising approaches to tackle this problem. Nevertheless, designing the learning algorithm to cope with the dynamic nature of the D2D network is a challenge. Current research using DL only assumes a static layout of the network without taking advantage of the correlations between the decisions in a dynamic network. Consequently, this paper proposes a sequence-to-sequence modelling (SSM) method for D2D scheduling using only distance information. The SSM processes the distance information as well as the previous scheduling de-cisions in a sequential manner with a feedback from the intermediate output, and models the correlations be-tween consecutive input information as well as the produced decisions. Simulation results show that the average sum rate of the SSM is about 95% of that achieved by the optimal scheduler and it requires at least 90% less resources than those required by other DL schedulers reported in the literature. Finally, the decision-making of SSM is explored for key input descriptors and an unsupervised decision-maker is explored, which is shown to produce reasonable results with minimal computational requirements.

关键词： Device-to-Device Machine learning Scheduling sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

Attention based sequence-to-sequence framework for auto image caption generation

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022年第1期43卷 159-170页

作者： Khan, Rashid Islam, M. Shujah Kanwal, Khadija Iqbal, Mansoor Hossain, Md Imran Ye, Zhongfu Univ Sci & Technol China Natl Engn Lab Speech & Language Informat Proc Hefei 230026 Anhui Peoples R China Anhui Agr Univ Hefei Anhui Peoples R China

Caption generation using an encoder-decoder approach has recently been extensively studied and implemented in various domains, including image captioning and code captioning. In this research article, we propose one particular approach for completing a capture generation task using an "attention"-based sequence-to-sequence framework that, when combined with a conventional encoder-decoder model, generates captions in an attention-based manner. ResNet-152 is a Convolutional Neural Network (CNN) based encoder that generates a comprehensive representation of an input image while embedding that into a fixed size length vector. To predict the next sentence, the decoder uses LSTM, a Recurrent Neural Network (RNN), and an attention-based mechanism to concentrate attention on certain sections of an image selectively. Define a set of epochs to 69, which should be enough for training the model to generate informative descriptions, and the validation loss has reached its minimum limit and no longer decreases. We present the datasets as well as the evaluation metrics, as well as quantitative and qualitative analysis. Experiments on the MSCOCO and Flickr8k benchmark datasets illustrate the model's efficacy in comparison to the baseline techniques. On MSCOCO, evaluation scores included BLEU-1 0.81, BLEU-2 0.61, BLEU-3 0.47, and 0.33 METEOR. For Flickr8k BLEU-1 0.68, BLEU-2 0.49, BLEU-3 0.41, METEOR 0.23, and 0.86 on SPICE. The proposed approach is comparable with several state-of-the-art methods in terms of standard evaluation metric, demonstrating that it can produce more accurate and richer captions.

关键词： Image captioning CNN LSTM sequence-to-sequence neural network

来源：评论

学校读者我要写书评

暂无评论

Faster Capacitated Arc Routing: A sequence-to-sequence Approach

引用

IEEE ACCESS 2022年 10卷 4777-4785页

作者： Hong, Wenjing Liu, Tonglin Southern Univ Sci & Technol Guangdong Prov Key Lab Brain Inspired Intelligent Dept Comp Sci & Engn Shenzhen 518055 Peoples R China Guangdong Hong Kong Macao Greater Bay Area Ctr Br Guangzhou 510515 Peoples R China Beijing Electromech Engn Inst Sci & Technol Complex Syst Control & Intelligent Beijing 100074 Peoples R China

The Capacitated Arc Routing Problem (CARP) is an NP-hard optimization problem that has been investigated for decades. Heuristic search methods are commonly used to solve it. However, given a CARP instance, most heuristic search algorithms require plenty of time to iteratively search for the solution from scratch, and hence may be impractical for emerging applications that need a solution to be obtained in a very short time period. In this work, a novel approach to efficiently solve CARP is presented. The proposed approach replaces the heuristic search process with the inference phase of a trained Deep Neural Network (DNN), which is trained to take a CARP instance as the input and outputs a solution to the instance. In this way, CARP could be solved by a direct mapping rather than by iterative search, and hence could be more efficient and more easily accelerated by the use of GPUs. Empirical study shows that the DNN-based solver can achieve significant speed-up with minor performance loss, and up to hundreds of times acceleration in extreme cases.

关键词： Task analysis Heuristic algorithms Training Optimization Deep learning Routing Machine learning algorithms Capacitated arc routing problem sequence-to-sequence deep neural network

来源：评论

学校读者我要写书评

暂无评论

A sequence-to-sequence Approach with Mixed Pointers to Topic Segmentation and Segment Labeling 23

A Sequence-to-Sequence Approach with Mixed Pointers to Topic...

引用

29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

作者： Xia, Jinxiong Wang, Houfeng Peking Univ Sch Software & Microelect Beijing Peoples R China Peking Univ Sch Comp Sci Natl Key Lab Multimedia Informat Proc Beijing Peoples R China

ISBN: (纸本)9798400701030

Topic segmentation is the process of dividing a text into semantically coherent segments, and segment labeling involves assigning a topic label to each of these segments. Previous work on this task has included the use of sequence labeling, segment-extraction, and generative models. While these methods have yielded impressive results, existing generative models have struggled to accurately generate strings of segment boundaries, limiting their competitiveness in this area. In this paper, we present a novel sequence-to-sequence approach with Mixed Pointers (Seq2Seq-MP). Seq2SeqMP employs an encoder-decoder architecture with the pointer mechanism to generate both segment boundaries and topics, which allows for a more robust performance than string-generation models and can handle long-range dependencies better than sequence labeling and segment-extraction models. Additionally, we introduce the pairwise type encoding and type-aware relative position encoding to improve the fusion of type and position information, enhancing the interactions between sentences and topics in the encoder and decoder. Our experiments on public datasets show that Seq2Seq-MP outperforms the current state-of-the-art, with up to 2.9% and 4.0% improvements in p(k) and F-1, respectively.

关键词： Topic segmentation segment labeling sequence-to-sequence pointer networks

来源：评论

学校读者我要写书评

暂无评论

RASR2: The RWTH ASR Toolkit for Generic sequence-to-sequence Speech Recognition 24

RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence...

引用

Interspeech Conference

作者： Zhou, Wei Beck, Eugen Berger, Simon Schlueter, Ralf Ney, Hermann Rhein Westfal TH Aachen Dept Comp Sci Machine Learning & Human Language Technol D-52074 Aachen Germany AppTek GmbH D-52062 Aachen Germany

Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only. For closed-vocabulary scenarios, public tools supporting lexical-constrained decoding are usually only for classical ASR, or do not support all S2S models. To eliminate this restriction on research possibilities such as modeling unit choice, we present RASR2 in this work, a research-oriented generic S2S decoder implemented in C++. It offers a strong flexibility/compatibility for various S2S models, language models, label units/topologies and neural network architectures. It provides efficient decoding for both open- and closed-vocabulary scenarios based on a generalized search framework with rich support for different search modes and settings. We evaluate RASR2 with a wide range of experiments on both switchboard and Librispeech corpora. Our source code is public online.

关键词： speech recognition toolkit sequence-to-sequence decoder beam search RASR

来源：评论

学校读者我要写书评

暂无评论

sequence-to-sequence Learning for Deep Gaussian Process Based Speech Synthesis Using Self-Attention GP Layer 22

Sequence-to-Sequence Learning for Deep Gaussian Process Base...

引用

Interspeech Conference

作者： Nakamura, Taiki Koriyama, Tomoki Saruwatari, Hiroshi Univ Tokyo Grad Sch Informat Sci & Technol Tokyo Japan

ISBN: (纸本)9781713836902

This paper presents a speech synthesis method based on deep Gaussian process (DGP) and sequence-to-sequence (Seq2Seq) learning toward high-quality end-to-end speech synthesis. Feed-forward and recurrent models using DGP are known to produce more natural synthetic speech than deep neural networks (DNNs) because of Bayesian learning and kernel regression. However, such DGP models consist of a pipeline architecture of independent models, acoustic and duration models, and require a high level of expertise in text processing. The proposed model is based on Seq2Seq learning, which enables a unified training of acoustic and duration models. The encoder and decoder layers are represented by Gaussian process regressions (GPRs) and the parameters are trained as a Bayesian model. We also propose a self-attention mechanism with Gaussian processes to effectively model character-level input in the encoder. The subjective evaluation results show that the proposed Seq2Seq-SA-DGP can synthesize more natural speech than DNNs with self-attention and recurrent structures. Besides, Seq2Seq-SA-DGP reduces the smoothing problems of recurrent structures and is effective when a simple input for an end-to-end system is given.

关键词： speech synthesis deep Gaussian process sequence-to-sequence Bayesian deep model sequential modeling

来源：评论

学校读者我要写书评

暂无评论

Enhanced sequence-to-sequence Attention-Based PM2.5 Concentration Forecasting Using Spatiotemporal Data

引用

ATMOSPHERE 2024年第12期15卷 1469-1469页

作者： Kim, Baekcheon Kim, Eunkyeong Jung, Seunghwan Kim, Minseok Kim, Jinyong Kim, Sungshin Pusan Natl Univ Dept Elect & Elect Engn Busan 46241 South Korea

Severe air pollution problems continue to increase because of accelerated industrialization and urbanization. Specifically, fine particulate matter (PM2.5) causes respiratory and cardiovascular diseases, and according to the World Health Organization (WHO), millions of premature deaths and significant health burdens annually. Therefore, PM2.5 concentration forecasting is essential. This study proposed a method to forecast PM2.5 concentrations one hour after using sequence-to-sequence Attention (Seq2Seq-attention). The proposed method selects neighboring stations using minimum redundancy maximum relevance (mRMR) and integrates their data using a convolutional neural network (CNN). The proposed attention score and Seq2Seq are used on the integrated data to forecast PM2.5 concentration after one hour. The performance of the proposed method is validated through two case studies. The first comparison evaluated the performance of the conventional attention score against the proposed attention scores. The second comparison evaluated the forecasting results with and without considering neighboring stations. The first study showed that the proposed attention score improved the performance index (Root Mean Square Error (RMSE): 3.48%p, Mean Absolute Error (MAE): 8.60%p, R-2: 0.49%p, relative Root Mean Square Error (rRMSE): 3.64%p, Percent Bias (PBIAS): 59.29%p). The second case study showed that considering neighboring stations' data can be more effective in forecasting than considering that of a standalone station (RMSE: 5.49%p, MAE: 0.51%p, R-2: 0.67%p, rRMSE: 5.44%p, PBIAS: 46.56%p). This confirmed that the proposed method can effectively forecast the PM2.5 concentration after one hour.

关键词： PM2.5 concentration forecasting minimum redundancy maximum relevance sequence-to-sequence attention method

来源：评论

学校读者我要写书评

暂无评论

BARTpho: Pre-trained sequence-to-sequence Models for Vietnamese 23

BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnam...

引用

Interspeech Conference

作者： Nguyen Luong Tran Duong Minh Le Dat Quoc Nguyen VinAI Res Hanoi Vietnam

We present BARTpho with two versions, BARTpho(syllable) and BARTpho(word), which are the first public large-scale monolingual sequence-to-sequence models pre-trained for Vietnamese. BARTpho uses the "large" architecture and the pre-training scheme of the sequence-to-sequence denoising autoencoder BART, thus it is especially suitable for generative NLP tasks. We conduct experiments to compare our BARTpho with its competitor mBART on a downstream task of Vietnamese text summarization and show that: in both automatic and human evaluations, BARTpho outperforms the strong baseline mBART and improves the state-of-the-art. We further evaluate and compare BARTpho and mBART on the Vietnamese capitalization and punctuation restoration tasks and also find that BARTpho is more effective than mBART on these two tasks. We publicly release BARTpho to facilitate future research and applications of generative Vietnamese NLP tasks.

关键词： BARTpho sequence-to-sequence Vietnamese Pre-trained models Text summarization Capitalization Punctuation restoration

来源：评论

学校读者我要写书评

暂无评论

DISTILLING sequence-to-sequence VOICE CONVERSION MODELS FOR STREAMING CONVERSION APPLICATIONS

DISTILLING SEQUENCE-TO-SEQUENCE VOICE CONVERSION MODELS FOR ...

引用

IEEE Spoken Language Technology Workshop (SLT)

作者： Tanaka, Kou Kameoka, Hirokazu Kaneko, Takuhiro Seki, Shogo NTT Corp NTT Commun Sci Labs Tokyo Japan

ISBN: (纸本)9798350396904

This paper describes a method for distilling a recurrentbased sequence-to-sequence (S2S) voice conversion (VC) model. Although the performance of recent VCs is becoming higher quality, streaming conversion is still a challenge when considering practical applications. To achieve streaming VC, the conversion model needs a streamable structure, a causal layer rather than a non-causal layer. Motivated by this constraint and recent advances in S2S learning, we apply the teacher-student framework to recurrent-based S2S-VC models. A major challenge is how to minimize degradation due to the use of causal layers which masks future input information. Experimental evaluations show that except for male-to-female speaker conversion, our approach is able to maintain the teacher model's performance in terms of subjective evaluations despite the streamable student model structure. Audio samples can be accessed on http://***/people/tanaka. ko/projects/dists2svc.

关键词： Voice conversion sequence-to-sequence learning distillation streaming conversion

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：