检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

76 篇 会议
62 篇 期刊文献
1 篇 学位论文

馆藏范围

139 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

135 篇 工学
- 94 篇 计算机科学与技术...
- 51 篇 电气工程
- 22 篇 信息与通信工程
- 18 篇 软件工程
- 14 篇 控制科学与工程
- 9 篇 交通运输工程
- 6 篇 石油与天然气工程
- 5 篇 测绘科学与技术
- 4 篇 动力工程及工程热...
- 4 篇 土木工程
- 2 篇 机械工程
- 2 篇 电子科学与技术（可...
- 2 篇 船舶与海洋工程
- 2 篇 生物医学工程（可授...
- 2 篇 安全科学与工程
- 1 篇 光学工程
28 篇 理学
- 19 篇 物理学
- 3 篇 地球物理学
- 2 篇 数学
- 2 篇 化学
- 1 篇 地理学
- 1 篇 大气科学
- 1 篇 海洋科学
23 篇 医学
- 19 篇 临床医学
- 3 篇 基础医学(可授医学...
9 篇 管理学
- 9 篇 管理科学与工程(可...
- 2 篇 图书情报与档案管...
2 篇 文学
- 2 篇 外国语言文学
1 篇 经济学
- 1 篇 理论经济学
1 篇 教育学
- 1 篇 教育学

主题

139 篇 sequence-to-sequ...
18 篇 deep learning
17 篇 attention mechan...
12 篇 speech synthesis
10 篇 natural language...
8 篇 speech recogniti...
7 篇 transformer
7 篇 attention
6 篇 training
5 篇 transformers
5 篇 decoding
5 篇 feature extracti...
4 篇 semantic segment...
4 篇 transfer learnin...
4 篇 machine learning
4 篇 text-to-speech s...
4 篇 neural machine t...
3 篇 machine translat...
3 篇 automated progra...
3 篇 lstm

机构

3 篇 google mountain ...
3 篇 google llc mount...
2 篇 google res mount...
2 篇 soongsil univ de...
2 篇 nara inst sci & ...
2 篇 soongsil univ sc...
2 篇 nagoya univ info...
2 篇 natl inst inform...
2 篇 univ trento dept...
2 篇 cent china norma...
2 篇 south china univ...
2 篇 fdn bruno kessle...
1 篇 columbia univers...
1 篇 indian inst trop...
1 篇 fdn bruno kessle...
1 篇 city univ hong k...
1 篇 chung ang univ g...
1 篇 jd intelligent c...
1 篇 shandong enginee...
1 篇 ping an technol ...

作者

4 篇 jia ye
4 篇 weiss ron j.
4 篇 bovolo francesca
4 篇 ghosh raktim
4 篇 biadsy fadi
3 篇 moreno pedro j.
3 篇 wu yonghui
2 篇 yamagishi junich...
2 篇 johnson melvin
2 篇 chen youzheng
2 篇 tan xiaoyu
2 篇 ramabhadran bhuv...
2 篇 nakamura satoshi
2 篇 jiang liyang
2 篇 li min
2 篇 lee soowon
2 篇 okamoto takuma
2 篇 kawahara tatsuya
2 篇 wu chung-hsien
2 篇 doshi rohan

语言

138 篇 英文
1 篇 德文
1 篇 法文

检索条件"主题词=sequence-to-sequence Model"

共 139 条记录，以下是91-100 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Context- and sequence-Aware Convolutional Recurrent Encoder for Neural Machine Translation 21

Context- and Sequence-Aware Convolutional Recurrent Encoder ...

引用

36th Annual ACM Symposium on Applied Computing (SAC)

作者： Mallick, Ritam Susan, Seba Agrawal, Vaibhaw Garg, Rizul Rawal, Prateek Delhi Technol Univ Rohini Delhi 12 India

ISBN: (纸本)9781450381048

Neural Machine Translation(1) model is a sequence-to-sequence converter based on neural networks. Existing models use recurrent neural networks to construct both the encoder and decoder modules. In alternative research, the recurrent networks were substituted by convolutional neural networks for capturing the syntactic structure in the input sentence and decreasing the processing time. We incorporate the goodness of both approaches by proposing a convolutional-recurrent encoder for capturing the context information as well as the sequential information from the source sentence. Word embedding and position embedding of the source sentence is performed prior to the convolutional encoding layer which is basically a n-gram feature extractor capturing phrase-level context information. The rectified output of the convolutional encoding layer is added to the original embedding vector, and the sum is normalized by layer normalization. The normalized output is given as a sequential input to the recurrent encoding layer that captures the temporal information in the sequence. For the decoder, we use the attention-based recurrent neural network. Translation task on the German-English dataset verifies the efficacy of the proposed approach from the higher BLEU scores achieved as compared to the state of the art.

关键词： Neural machine translation convolutional recurrent encoder decoder context sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency 21

High Quality Streaming Speech Synthesis with Low, Sentence-L...

引用

Interspeech Conference

作者： Ellinas, Nikolaos Vamvoukakis, Georgios Markopoulos, Konstantinos Chalamandaris, Aimilios Maniati, Georgia Kakoulidis, Panos Raptis, Spyros Sung, June Sig Park, Hyoungmin Tsiakoulis, Pirros Samsung Elect Innoet Attica Greece Samsung Elect Mobile Commun Business Suwon Gyeonggi Do South Korea

ISBN: (纸本)9781713820697

This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based sequence-to-sequence acoustic model and the LPCNet vocoder for waveform generation. An acoustic model architecture that adopts modules from both the Tacotron 1 and 2 models is proposed, while stability is ensured by using a recently proposed purely location-based attention mechanism, suitable for arbitrary sentence length generation. During inference, the decoder is unrolled and acoustic feature generation is performed in a streaming manner, allowing for a nearly constant latency which is independent from the sentence length. Experimental results show that the acoustic model can produce feature sequences with minimal latency about 31 times faster than real-time on a computer CPU and 6.5 times on a mobile CPU, enabling it to meet the conditions required for real-time applications on both devices. The full end-to-end system can generate almost natural quality speech, which is verified by listening tests.

关键词： Text-to-speech synthesis real-time sequence-to-sequence model streaming inference end-to-end TTS

来源：评论

学校读者我要写书评

暂无评论

Personalized Dialogue Response Generation Learned from Monologues 20

Personalized Dialogue Response Generation Learned from Monol...

引用

Interspeech Conference

作者： Su, Feng-Guang Hsu, Aliyah R. Tuan, Yi-Lin Lee, Hung-Yi Natl Taiwan Univ Dept Elect Engn Taipei Taiwan

Personalized responses are essential for having an informative and human-like conversation. Because it is difficult to collect a large amount of dialogues involved with specific speakers, it is desirable that chatbot can learn to generate personalized responses simply from monologues of individuals. In this paper, we propose a novel personalized dialogue generation method which reduces the training data requirement to dialogues without speaker information and monologues of every target speaker. In the proposed approach, a generative adversarial network ensures the responses containing recognizable personal characteristics of the target speaker, and a backward SEQ2SEQ model reconstructs the input message for keeping the coherence of the generated responses. The proposed model demonstrates its flexibility to respond to open-domain conversations, and the experimental results show that the proposed method performs favorably against prior work in coherence, personality classification, and human evaluation.

关键词： personalized dialogue generation generative adversarial network sequence-to-sequence model monologues

来源：评论

学校读者我要写书评

暂无评论

LEVERAGING WEAKLY SUPERVISED DATA TO IMPROVE END-TO-END SPEECH-TO-TEXT TRANSLATION 44

LEVERAGING WEAKLY SUPERVISED DATA TO IMPROVE END-TO-END SPEE...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Jia, Ye Johnson, Melvin Macherey, Wolfgang Weiss, Ron J. Cao, Yuan Chiu, Chung-Cheng Ari, Naveen Laurenzo, Stella Wu, Yonghui Google Res Mountain View CA 94043 USA

ISBN: (纸本)9781479981311

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of error compounding. However, the quality of end-to-end ST is often limited by a paucity of training data, since it is difficult to collect large parallel corpora of speech and translated transcript pairs. Previous studies have proposed the use of pre-trained components and multi-task learning in order to benefit from weakly supervised training data, such as speech-to-transcript or text-to-foreign-text pairs. In this paper, we demonstrate that using pre-trained MT or text-to-speech (TTS) synthesis models to convert weakly supervised data into speech-to-translation pairs for ST training can be more effective than multi-task learning. Furthermore, we demonstrate that a high quality end-to-end ST model can be trained using only weakly supervised datasets, and that synthetic data sourced from unlabeled monolingual text or speech can be used to improve performance. Finally, we discuss methods for avoiding overfitting to synthetic speech with a quantitative ablation study.

关键词： Speech translation sequence-to-sequence model weakly supervised learning synthetic training data

来源：评论

学校读者我要写书评

暂无评论

Nonintrusive Load Monitoring Based on Deep Learning 1

引用

6th ECML PKDD International Workshop on Data Analytics for Renewable Energy Integration (DARE)

作者： Wang, Ke Zhong, Haiwang Yu, Nanpeng Xia, Qing Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Tsinghua Univ State Key Lab Control & Simulat Power Syst & Gene Beijing 100084 Peoples R China Univ Calif Riverside Riverside CA 92521 USA

ISBN: (数字)9783030043032

ISBN: (纸本)9783030043032;9783030043025

This paper presents a novel nonintrusive load monitoring method based on deep learning. Unlike the existing work based on convolutional neural network and recurrent neural network with fully connected layers, this paper develops a deep neural network based on sequence-to-sequence model and attention mechanism to perform nonintrusive load monitoring. The overall framework can be divided into three layers. In the first layer, the input active power time sequence is embedded into a group of high dimensional vectors. In the second layer, the vectors are encoded by a bi-directional LSTM layer, and the N encoded vectors are added up to form a dynamic context vector according to its weights calculated by the attention mechanism. In the third layer, an LSTM-based decoder utilizes the dynamic context vector to calculate the disaggregated power consumption at every time step. The proposed method is trained and tested on REFITPowerData dataset. The results show that compared to the state-of-the-art methods, the proposed method significantly increases the accuracy of the estimation for the disaggregated power value and decreases the misjudge rate by 10% to 20%.

关键词： Nonintrusive load monitoring Deep learning sequence-to-sequence model Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Attention model for articulatory features detection 20

Attention model for articulatory features detection

引用

Interspeech Conference

作者： Karaulov, Ievgen Tkanov, Dmytro Sciforce Kharkiv Ukraine

Articulatory distinctive features, as well as phonetic transcription, play important role in speech-related tasks: computer-assisted pronunciation training, text-to-speech conversion (TTS), studying speech production mechanisms, speech recognition for low-resourced languages. End-to-end approaches to speech-related tasks got a lot of traction in recent years. We apply Listen, Attend and Spell (LAS) [1] architecture to phones recognition on a small small training set, like TIMIT [2]. Also, we introduce a novel decoding technique that allows to train manners and places of articulation detectors end-to-end using attention models. We also explore joint phones recognition and articulatory features detection in multitask learning setting.

关键词： manners of articulation places of articulation sequence-to-sequence model multitask learning low-resource speech recognition phones recognition

来源：评论

学校读者我要写书评

暂无评论

MTrajRec: Map-Constrained Trajectory Recovery via Seq2Seq Multi-task Learning 21

MTrajRec: Map-Constrained Trajectory Recovery via Seq2Seq Mu...

引用

27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

作者： Ren, Huimin Ruan, Sijie Li, Yanhua Bao, Jie Meng, Chuishi Li, Ruiyuan Zheng, Yu Worcester Polytech Inst Worcester MA 01609 USA Xidian Univ Xian Shaanxi Peoples R China Chongqing Univ Chongqing Peoples R China JD Intelligent Cities Res Beijing Peoples R China

ISBN: (纸本)9781450383325

With the increasing adoption of GPS modules, there are a wide range of urban applications based on trajectory data analysis, such as vehicle navigation, travel time estimation, and driver behavior analysis. The effectiveness of urban applications relies greatly on the high sampling rates of trajectories precisely matched to the map. However, a large number of trajectories are collected under a low sampling rate in real-world practice, due to certain communication loss and energy constraints. To enhance the trajectory data and support the urban applications more effectively, many trajectory recovery methods are proposed to infer the trajectories in free space. In addition, the recovered trajectory still needs to be mapped to the road network, before it can be used in the applications. However, the two-stage pipeline, which first infers high-sampling-rate trajectories and then performs the map matching, is inaccurate and inefficient. In this paper, we propose a Map-constrained Trajectory Recovery framework, MTrajRec, to recover the fine-grained points in trajectories and map match them on the road network in an end-to-end manner. MTrajRec implements a multi-task sequence-to-sequence learning architecture to predict road segment and moving ratio simultaneously. Constraint mask, attention mechanism, and attribute module are proposed to overcome the limits of coarse grid representation and improve the performance. Extensive experiments based on large-scale real-world trajectory data confirm the effectiveness and efficiency of our approach.

关键词： Trajectory recovery Road network Multi-task learning sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-band Multi-time LPCNet 22

Triple M: A Practical Text-to-speech Synthesis System With M...

引用

Interspeech Conference

作者： Lin, Shilun Xie, Fenglong Meng, Li Li, Xinhui Lu, Li Tencent Beijing Peoples R China

ISBN: (纸本)9781713836902

In this work, a robust and efficient text-to-speech (TTS) synthesis system named Triple M is proposed for large-scale online application. The key components of Triple M are: 1) A sequence-to-sequence model adopts a novel multi-guidance attention to transfer complementary advantages from guiding attention mechanisms to the basic attention mechanism without in-domain performance loss and online service modification. Compared with single attention mechanism, multi-guidance attention not only brings better naturalness to long sentence synthesis, but also reduces the word error rate by 26.8%. 2) A new efficient multi-band multi-time vocoder framework, which reduces the computational complexity from 2.8 to 1.0 GFLOP and speeds up LPCNet by 2.75x on a single CPU.

关键词： Speech synthesis sequence-to-sequence model attention transfer learning vocoder LPCNet

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMER-BASED TEXT-TO-SPEECH WITH WEIGHTED FORCED ATTENTION

TRANSFORMER-BASED TEXT-TO-SPEECH WITH WEIGHTED FORCED ATTENT...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Okamoto, Takuma Toda, Tomoki Shiga, Yoshinori Kawai, Hisashi Natl Inst Informat & Commun Technol Tokyo Japan Nagoya Univ Informat Technol Ctr Nagoya Aichi Japan

ISBN: (纸本)9781509066315

This paper investigates state-of-the-art Transformer- and FastSpeech-based high-fidelity neural text-to-speech (TTS) with full-context label input for pitch accent languages. The aim is to realize faster training than conventional Tacotron-based models. Introducing phoneme durations into Tacotron-based TTS models improves both synthesis quality and stability. Therefore, a Transformer-based acoustic model with weighted forced attention obtained from phoneme durations is proposed to improve synthesis accuracy and stability, where both encoder-decoder attention and forced attention are used with a weighting factor. Furthermore, FastSpeech without a duration predictor, in which the phoneme durations are predicted by another conventional model, is also investigated. The results of experiments using a Japanese female corpus and the WaveGlow vocoder indicate that the proposed Transformer using forced attention with a weighting factor of 0.5 outperforms other models, and removing the duration predictor from FastSpeech improves synthesis quality, although the proposed weighted forced attention does not improve synthesis stability.

关键词： Speech synthesis sequence-to-sequence model Transformer forced alignment weighted forced attention

来源：评论

学校读者我要写书评

暂无评论

FORWARD ATTENTION IN sequence-TO-sequence ACOUSTIC modelING FOR SPEECH SYNTHESIS

FORWARD ATTENTION IN SEQUENCE-TO-SEQUENCE ACOUSTIC MODELING ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Zhang, Jing-Xuan Ling, Zhen-Hua Dai, Li-Rong Univ Sci & Technol China Natl Engn Lab Speech & Language Informat Proc Hefei Anhui Peoples R China

ISBN: (纸本)9781538646588

This paper proposes a forward attention method for the sequence-to-sequence acoustic modeling of speech synthesis. This method is motivated by the nature of the monotonic alignment from phone sequences to acoustic sequences. Only the alignment paths that satisfy the monotonic condition are taken into consideration at each decoder timestep. The modified attention probabilities at each timestep are computed recursively using a forward algorithm. A transition agent for forward attention is further proposed, which helps the attention mechanism to make decisions whether to move forward or stay at each decoder timestep. Experimental results show that the proposed forward attention method achieves faster convergence speed and higher stability than the baseline attention method. Besides, the method of forward attention with transition agent can also help improve the naturalness of synthetic speech and control the speed of synthetic speech effectively.

关键词： sequence-to-sequence model encoder-decoder attention speech synthesis

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共14页 << < 5 6 7 8 9 10 11 12 13 14 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：