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81-90 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：

A Comparative Study on Transformer Versus sequence to sequence in Machine Translation 1st

A Comparative Study on Transformer Versus Sequence to Sequen...

引用

1st International Conference on Industrial IoT, Big Data and Supply Chain (IIoTBDSC)

作者： Jiang, Hao Zhao, Su Fang, Da Zhang, Chao Duan, Jianjin Yunnan Normal Univ Kunming Yunnan Peoples R China

ISBN: (纸本)9789813361430;9789813361416;9789813361409

Machine translation is the process of translating one natural language into another natural language. In the experiment, machine translation tasks were performed on the English to German data set and the English to Thai data set through the sequence-to-sequence model, the sequence-to-sequence model with attention mechanism and the transformer model. Through the analysis of the experimental data, it is concluded that the transformer model is not only better than the first two models in the performance of machine translation, but also the structural characteristics of the transformer model. When the data set is a relatively rare English to Thai data set, the transformer model is collected, and the impact of the result is less than the first two, which proves that the transformer model improves the quality of machine translation.

关键词： Attention BLEU score sequence-to-sequence model Transformer

来源：评论

学校读者我要写书评

暂无评论

TEXTUAL ECHO CANCELLATION

TEXTUAL ECHO CANCELLATION

引用

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

作者： Ding, Shaojin Jia, Ye Hu, Ke Wang, Quan Google LLC Mountain View CA 94043 USA

ISBN: (纸本)9781665437394

In this paper, we propose Textual Echo Cancellation (TEC) - a framework for cancelling the text-to-speech (TTS) playback echo(1) from overlapping speech recordings. Such a system can largely improve speech recognition performance and user experience for intelligent devices such as smart speakers, as the user can talk to the device while the device is still playing the TI'S signal responding to the previous query. We implement this system by using a novel sequence-to-sequence model with multi-source attention that takes both the microphone mixture signal and source text of the TTS playback as inputs, and predicts the enhanced audio. Experiments show that the textual information of the TTS playback is critical to enhancement performance. Besides, the text sequence is much smaller in size compared with the raw acoustic signal of the TTS playback, and can be immediately transmitted to the device or ASR server even before the playback is synthesized. Therefore, our proposed approach effectively reduces Internet communication and latency compared with alternative approaches such as acoustic echo cancellation (AEC).

关键词： echo cancellation multi-source attention sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

ITAR: A Method for Indoor RFID Trajectory Automatic Recovery 18th

ITAR: A Method for Indoor RFID Trajectory Automatic Recovery

引用

18th European-Alliance-for-Innovation (EAI) International Conference on Collaborative Computing - Networking, Applications and Worksharing (CollaborateCom)

作者： Cao, Ziwen Wang, Siye Sun, Degang Zhang, Yanfang Feng, Yue Jiang, Shang Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing Peoples R China

ISBN: (纸本)9783031243851;9783031243868

With the increasing popularity of Radio Frequency Identification (RFID) technology, indoor applications based on RFID trajectory data analysis are becoming more and more extensive, such as personnel location, tracking, and heat map analysis. The effectiveness of indoor applications relies greatly on high-quality trajectory data. However, due to the constraints of the device and environment, RFID readers will miss reading data in real-world practice, which leads to a large number of indoor trajectories that are incomplete. To enhance trajectory data and support indoor applications more efficiently, many trajectory recovery methods to infer trajectories in free space have been proposed. However, existing methods cannot achieve automated inference and have low accuracy in inferring indoor trajectories. In this paper, we propose an Indoor Trajectory Automatic Recovery framework, ITAR, to recover missing points in indoor trajectories. ITAR adopts a sequence-to-sequence learning architecture to generate complete trajectories. We first construct a directed graph for each trajectory and use a graph neural network to capture complex location transition patterns. Then, we propose a multi-head attention mechanism to capture long-term correlations among trajectory points to improve performance. We conduct extensive experiments on synthetic and real datasets, and the results show that ITAR is superior in performance and robustness.

关键词： Trajectory recovery sequence-to-sequence model Radio frequency identification Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Neural Machine Translation for Multilingual Grapheme-to-Phoneme Conversion 20

Neural Machine Translation for Multilingual Grapheme-to-Phon...

引用

Interspeech Conference

作者： Sokolov, Alex Rohlin, Tracy Rastrow, Ariya Amazoncom Inc Seattle WA 98170 USA

Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the pronunciation lexicons (mappings like”e c h o” → ”E k oU”). Most G2P systems are monolingual and based on traditional joint-sequence based n-gram models [1, 2]. As an alternative, we present a single end-to-end trained neural G2P model that shares same encoder and decoder across multiple languages. This allows the model to utilize a combination of universal symbol inventories of Latin-like alphabets and cross-linguistically shared feature representations. Such model is especially useful in the scenarios of low resource languages and code switching/foreign words, where the pronunciations in one language need to be adapted to other locales or accents. We further experiment with word language distribution vector as an additional training target in order to improve system performance by helping the model decouple pronunciations across a variety of languages in the parameter space. We show 7.2% average improvement in phoneme error rate over low resource languages and no degradation over high resource ones compared to monolingual baselines. Copyright © 2019 ISCA

关键词： grapheme-to-phoneme conversion sequence-to-sequence model multilingual machine translation pronunciation generation

来源：评论

学校读者我要写书评

暂无评论

Generating Titles for Web Tables 19

Generating Titles for Web Tables

引用

World Wide Web Conference (WWW)

作者： Hancock, Braden Lee, Hongrae Yu, Cong Stanford Univ Stanford CA 94305 USA Google Mountain View CA USA Google New York NY USA

ISBN: (纸本)9781450366748

Descriptive titles provide crucial context for interpreting tables that are extracted from web pages and are a key component of search features such as tabular featured snippets from Google and Bing. Prior approaches have attempted to produce titles by selecting existing text snippets associated with the table. These approaches, however, are limited by their dependence on suitable titles existing a priori. In our user study, we observe that the relevant information for the title tends to be scattered across the page, and often more than 80% of the time does not appear verbatim anywhere in the page. We propose instead the application of a sequence-to-sequence neural network model as a more generalizable approach for generating high-quality table titles. This is accomplished by extracting many text snippets that have potentially relevant information to the table, encoding them into an input sequence, and using both copy and generation mechanisms in the decoder to balance relevance and readability of the generated title. We validate this approach with human evaluation on sample web tables and report that while sequence models with only a copy mechanism or only a generation mechanism are easily outperformed by simple selection-based baselines, the model with both capabilities performs the best, approaching the quality of crowdsourced titles while training on fewer than ten thousand examples. To the best of our knowledge, the proposed technique is the first to consider text-generation methods for table titles, and establishes a new state of the art.

关键词： title generation web tables table summarization table understanding sequence-to-sequence model text generation pointer-generator network natural language generation

来源：评论

学校读者我要写书评

暂无评论

ENHANCING HYBRID SELF-ATTENTION STRUCTURE WITH RELATIVE-POSITION-AWARE BIAS FOR SPEECH SYNTHESIS 44

ENHANCING HYBRID SELF-ATTENTION STRUCTURE WITH RELATIVE-POSI...

引用

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

作者： Yang, Shan Lu, Heng Kang, Shiying Xie, Lei Yu, Dong Northwestern Polytech Univ Sch Comp Sci Xian Shaanxi Peoples R China

ISBN: (纸本)9781479981311

Compared with the conventional "front-end"-"back-end"" vocoder" structure, based on the attention mechanism, end-to-end speech synthesis systems directly train and synthesize from text sequence to the acoustic feature sequence as a whole. Recently, a more calculation efficient end-to-end architecture named transformer, which is solely based on self-attention, was proposed to model global dependencies between the input and output sequences. However, although with many advantages, transformer lacks position information in its structure. Moreover, the weighted sum form in self-attention may disperse the attention to the whole input sequence other than focusing on the more important neighbouring positions. In order to solve the above problems, this paper introduces a hybrid self-attention structure which combines self-attention with the recurrent neural networks (RNNs). We further enhance the proposed structure with relative-position-aware biases. Mean opinion score (MOS) test results indicate that by enhancing hybrid self-attention structure with relative-position-aware biases, the proposed system achieves the best performance with only 0.11 MOS score lower than natural recording.

关键词： text-to-speech synthesis sequence-to-sequence model self-attention relative-position-aware representation

来源：评论

学校读者我要写书评

暂无评论

A NEURAL ACOUSTIC ECHO CANCELLER OPTIMIZED USING AN AUTOMATIC SPEECH RECOGNIZER AND LARGE SCALE SYNTHETIC DATA

A NEURAL ACOUSTIC ECHO CANCELLER OPTIMIZED USING AN AUTOMATI...

引用

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

作者： Howard, Nathan Park, Alex Shabestary, Turaj Zakizadeh Gruenstein, Alexander Prabhavalkar, Rohit Google Inc Mountain View CA 94043 USA

ISBN: (纸本)9781728176055

We consider the problem of recognizing speech utterances spoken to a device which is generating a known sound waveform;for example, recognizing queries issued to a digital assistant which is generating responses to previous user inputs. Previous work has proposed building acoustic echo cancellation (AEC) models for this task that optimize speech enhancement metrics using both neural network as well as signal processing approaches. Since our goal is to recognize the input speech, we consider enhancements which improve word error rates (WERs) when the predicted speech signal is passed to an automatic speech recognition (ASR) model. First, we augment the loss function with a term that produces outputs useful to a pre-trained ASR model and show that this augmented loss function improves WER metrics. Second, we demonstrate that augmenting our training dataset of real world examples with a large synthetic dataset improves performance. Crucially, applying SpecAugment style masks to the reference channel during training aids the model in adapting from synthetic to real domains. In experimental evaluations, we find the proposed approaches improve performance, on average, by 57% over a signal processing baseline and 45% over the neural AEC model without the proposed changes.

关键词： Acoustic echo cancellation deep learning sequence-to-sequence model multi-task loss acoustic simulation

来源：评论

学校读者我要写书评

暂无评论

TACOTRON-BASED ACOUSTIC model USING PHONEME ALIGNMENT FOR PRACTICAL NEURAL TEXT-TO-SPEECH SYSTEMS

TACOTRON-BASED ACOUSTIC MODEL USING PHONEME ALIGNMENT FOR PR...

引用

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

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)9781728103068

Although sequence-to-sequence (seq2seq) models with attention mechanism in neural text-to-speech (TTS) systems, such as Tacotron 2, can jointly optimize duration and acoustic models, and realize high-fidelity synthesis compared with conventional durationacoustic pipeline models, these involve a risk that speech samples cannot be sometimes successfully synthesized due to the attention prediction errors. Therefore, these seq2seq models cannot be directly introduced in practical TTS systems. On the other hand, the conventional pipeline models are broadly used in practical TTS systems since there are few crucial prediction errors in the duration model. For realizing high-quality practical TTS systems without attention prediction errors, this paper investigates Tacotron-based acoustic models with phoneme alignment instead of attention. The phoneme durations are first obtained from HMM-based forced alignment and the duration model is a simple bidirectional LSTM-based network. Then, a seq2seq model with forced alignment instead of attention is investigated and an alternative model with Tacotron decoder and phoneme duration is proposed. The results of experiments with full-context label input using WaveGlow vocoder indicate that the proposed model can realize a high-fidelity TTS system for Japanese with a real-time factor of 0.13 using a GPU without attention prediction errors compared with the seq2seq models.

关键词： Speech synthesis neural text-to-speech duration model forced alignment sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

A Survey of Research and Application of NLP-based Machine Translation 6

A Survey of Research and Application of NLP-based Machine Tr...

引用

6th International Conference on Natural Language Processing (ICNLP)

作者： Liu, Youyao Ma, Yuechi Zhou, Sicong Luo, Xun Xian Univ Posts & Telecommun Sch Elect Engn Xian Peoples R China

ISBN: (纸本)9798350349122;9798350349115

Machine translation is the process of using computers to convert one natural language into another natural language, shouldering the important task of building a language communication bridge. It has always been a concern research direction in natural language processing. As the latest paradigm of machine translation, neural machine translation completely relies on a neural network to execute the translation process from the source language to the target language. Thanks to the development of artificial intelligence, rich research results have been achieved in recent years, effectively alleviating the bottleneck problem of statistical machine translation. This paper first compares neural machine translation with other machine translation methods, then introduces the mainstream neural machinetranslation models, and finally introduces the problems and challenges faced by neural machine translation.

关键词： machine translation neural machine translation sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Personalized Query Suggestions 20

Personalized Query Suggestions

引用

43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Zhong, Jianling Guo, Weiwei Gao, Huiji Long, Bo LinkedIn Corp San Francisco CA 94105 USA

ISBN: (纸本)9781450380164

With the exponential growth of information on the internet, users have been relying on search engines for finding the precise documents. However, user queries are often short. The inherent ambiguity of short queries imposes great challenges for search engines to understand user intent. Query suggestion is one key technique for search engines to augment user queries so that they can better understand user intent. In the past, query suggestions have been relying on either term-frequency-based methods with little semantic understanding of the query, or word-embedding-based methods with little personalization efforts. Here, we present a sequence-to-sequence-model-based query suggestion framework that is capable of modeling structured, personalized features and unstructured query texts naturally. This capability opens up the opportunity to better understand query semantics and user intent at the same time. As the largest professional network, LINKEDIN has the advantage of utilizing a rich amount of accurate member profile information to personalize query suggestions. We applied this framework in the LINKEDIN production traffic and showed that personalized query suggestions significantly improved member search experience as measured by key business metrics at LINKEDIN.

关键词： Query suggestion sequence-to-sequence model Personalization Deep learning model deployment

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：