咨询与建议

限定检索结果

文献类型

  • 11 篇 会议
  • 6 篇 期刊文献

馆藏范围

  • 17 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 16 篇 工学
    • 12 篇 计算机科学与技术...
    • 5 篇 电气工程
    • 4 篇 软件工程
    • 1 篇 信息与通信工程
    • 1 篇 土木工程
    • 1 篇 交通运输工程
  • 5 篇 理学
    • 4 篇 物理学
    • 1 篇 系统科学
  • 3 篇 医学
    • 3 篇 临床医学
  • 1 篇 文学
    • 1 篇 外国语言文学
  • 1 篇 管理学
    • 1 篇 工商管理

主题

  • 17 篇 sequence-to-sequ...
  • 3 篇 hidden markov mo...
  • 3 篇 voice conversion
  • 2 篇 deep learning
  • 2 篇 feature extracti...
  • 1 篇 mobility
  • 1 篇 toolkit
  • 1 篇 extractive summa...
  • 1 篇 recurrent neural...
  • 1 篇 vq-wav2vec
  • 1 篇 vehicle induced ...
  • 1 篇 co-speech gestur...
  • 1 篇 variational auto...
  • 1 篇 public transport...
  • 1 篇 roads
  • 1 篇 task analysis
  • 1 篇 deep learning al...
  • 1 篇 innovation
  • 1 篇 location relativ...
  • 1 篇 quality metrics

机构

  • 3 篇 nagoya univ nago...
  • 1 篇 univ amsterdam
  • 1 篇 univ washington ...
  • 1 篇 carnegie mellon ...
  • 1 篇 ericsson res lun...
  • 1 篇 microsoft softwa...
  • 1 篇 netherlands canc...
  • 1 篇 acad sinica taiw...
  • 1 篇 rutgers state un...
  • 1 篇 iiit allahabad m...
  • 1 篇 the state key la...
  • 1 篇 tech univ dresde...
  • 1 篇 univ maryland co...
  • 1 篇 chi mei hosp tai...
  • 1 篇 department of ci...
  • 1 篇 bank new york me...
  • 1 篇 allen inst ai se...
  • 1 篇 virginia tech co...
  • 1 篇 hebrew univ jeru...
  • 1 篇 indian stat inst...

作者

  • 3 篇 huang wen-chin
  • 2 篇 toda tomoki
  • 1 篇 ramakrishnan nar...
  • 1 篇 shohel rana
  • 1 篇 mccormick hays s...
  • 1 篇 hayashi tomoki
  • 1 篇 xu shengzhe
  • 1 篇 weber alexander
  • 1 篇 liu xunying
  • 1 篇 wu jie
  • 1 篇 tsao yu
  • 1 篇 liu songxiang
  • 1 篇 thiele maik
  • 1 篇 busso carlos
  • 1 篇 scharenborg odet...
  • 1 篇 dawn sucheta
  • 1 篇 singh krishna pr...
  • 1 篇 yajnanarayana vi...
  • 1 篇 portet francois
  • 1 篇 jie he

语言

  • 17 篇 英文
检索条件"主题词=sequence-to-sequence modeling"
17 条 记 录,以下是1-10 订阅
排序:
Any-to-Many Voice Conversion With Location-Relative sequence-to-sequence modeling
收藏 引用
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2021年 29卷 1717-1728页
作者: Liu, Songxiang Cao, Yuewen Wang, Disong Wu, Xixin Liu, Xunying Meng, Helen Chinese Univ Hong Kong Dept Syst Engn & Engn Management Human Comp Commun Lab HCCL Hong Kong Peoples R China Univ Cambridge Engn Dept Cambridge CB2 1TN England
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach, which utilizes text supervision during training. In this approach, we combine a bottle-neck... 详细信息
来源: 评论
Seq2SeqPy: A Lightweight and Customizable Toolkit for Neural sequence-to-sequence modeling  12
Seq2SeqPy: A Lightweight and Customizable Toolkit for Neural...
收藏 引用
12th International Conference on Language Resources and Evaluation (LREC)
作者: Qader, Raheel Portet, Francois Labbe, Cyril Univ Grenoble Alpes LIG Grenoble France
We present Seq2SeqPy a lightweight toolkit for sequence-to-sequence modeling that prioritizes simplicity and ability to customize the standard architectures easily. The toolkit supports several known models such as Re... 详细信息
来源: 评论
Proactive Mobility Management of UEs using sequence-to-sequence modeling  27
Proactive Mobility Management of UEs using Sequence-to-Seque...
收藏 引用
28th National Conference on Communications (NCC)
作者: Yajnanarayana, Vijaya Ericsson Res Lund Sweden
Beyond 5G networks will operate at high frequencies with wide bandwidths. This brings both opportunities and challenges. Opportunities include high throughput connectivity with low latency. However, one of the main ch... 详细信息
来源: 评论
ANY-TO-ONE sequence-TO-sequence VOICE CONVERSION USING SELF-SUPERVISED DISCRETE SPEECH REPRESENTATIONS
ANY-TO-ONE SEQUENCE-TO-SEQUENCE VOICE CONVERSION USING SELF-...
收藏 引用
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
作者: Huang, Wen-Chin Wu, Yi-Chiao Hayashi, Tomoki Nagoya Univ Nagoya Aichi Japan
We present a novel approach to any-to-one (A2O) voice conversion (VC) in a sequence-to-sequence (seq2seq) framework. A2O VC aims to convert any speaker, including those unseen during training, to a fixed target speake... 详细信息
来源: 评论
Adversarially Trained Multi-Singer sequence-To-sequence Singing Synthesizer  21
Adversarially Trained Multi-Singer Sequence-To-Sequence Sing...
收藏 引用
Interspeech Conference
作者: Wu, Jie Luan, Jian Microsoft Software Technol Ctr Asia Xiaoice Redmond WA 98052 USA
This paper presents a high quality singing synthesizer that is able to model a voice with limited available recordings. Based on the sequence-to-sequence singing model, we design a multi-singer framework to leverage a... 详细信息
来源: 评论
Output Only Damage Detection of a Steel Truss Bridge Based on a Semisupervised BiLSTM modeling Scheme
收藏 引用
Structural Control and Health Monitoring 2025年 第1期2025卷
作者: Tazwar Bakhtiyar Zahid Shohel Rana Md. Niamul Haque Department of Civil Engineering Bangladesh University of Engineering and Technology (BUET) Dhaka 1000 Bangladesh buet.ac.bd
The application of machine learning techniques in bridge health monitoring is gaining widespread popularity as it overcomes the problems faced by conventional methods. However, the scarcity of labeled data for damaged... 详细信息
来源: 评论
SoURA: a user-reliability-aware social recommendation system based on graph neural network
收藏 引用
NEURAL COMPUTING & APPLICATIONS 2023年 第25期35卷 18533-18551页
作者: Dawn, Sucheta Das, Monidipa Bandyopadhyay, Sanghamitra Indian Stat Inst Machine Intelligence Unit Kolkata India
Exploiting user trust information for developing a recommendation system has gained increasing research interest in recent years. Due to the exchange of opinions about items over the social network, trust plays a cruc... 详细信息
来源: 评论
NetTraj: A Network-Based Vehicle Trajectory Prediction Model With Directional Representation and Spatiotemporal Attention Mechanisms
收藏 引用
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年 第9期23卷 14470-14481页
作者: Liang, Yuebing Zhao, Zhan Univ Hong Kong Dept Urban Planning & Design Hong Kong Peoples R China
Trajectory prediction of vehicles in city-scale road networks is of great importance to various location-based applications such as vehicle navigation, traffic management, and location-based recommendations. Existing ... 详细信息
来源: 评论
Sequential modeling by Leveraging Non-Uniform Distribution of Speech Emotion
收藏 引用
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2023年 31卷 1087-1099页
作者: Lin, Wei-Cheng Busso, Carlos Univ Texas Dallas Erik Jonsson Sch Engn & Comp Sci Richardson TX 75080 USA
The expression and perception of human emotions are not uniformly distributed over time. Therefore, tracking local changes of emotion within a segment can lead to better models for speech emotion recognition (SER), ev... 详细信息
来源: 评论
ML-assisted Optimization of Securities Lending  23
ML-assisted Optimization of Securities Lending
收藏 引用
4th ACM International Conference on AI in Finance (ICAIF)
作者: Prasad, Abhinav Arunachalam, Prakash Motamedi, Ali Bhattacharya, Ranjeeta Liu, Beibei McCormick, Hays Skip Xu, Shengzhe Muralidhar, Nikhil Ramakrishnan, Naren Bank New York Mellon New York NY 10166 USA Virginia Tech Comp Sci Arlington VA USA Stevens Inst Technol Comp Sci Hoboken NJ USA
This paper presents an integrated methodology to forecast the direction and magnitude of movements of lending rates in security markets. We develop a sequence-to-sequence (seq2seq) modeling framework that integrates f... 详细信息
来源: 评论