咨询与建议

限定检索结果

文献类型

  • 328 篇 会议
  • 129 篇 期刊文献

馆藏范围

  • 457 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 320 篇 工学
    • 241 篇 计算机科学与技术...
    • 210 篇 软件工程
    • 98 篇 信息与通信工程
    • 27 篇 生物工程
    • 18 篇 控制科学与工程
    • 17 篇 化学工程与技术
    • 16 篇 电气工程
    • 14 篇 电子科学与技术(可...
    • 13 篇 仪器科学与技术
    • 11 篇 生物医学工程(可授...
    • 7 篇 机械工程
    • 7 篇 建筑学
    • 6 篇 安全科学与工程
    • 5 篇 土木工程
    • 5 篇 农业工程
  • 170 篇 理学
    • 122 篇 物理学
    • 58 篇 数学
    • 32 篇 生物学
    • 22 篇 统计学(可授理学、...
    • 17 篇 化学
    • 10 篇 系统科学
  • 78 篇 管理学
    • 69 篇 图书情报与档案管...
    • 6 篇 管理科学与工程(可...
  • 15 篇 医学
    • 13 篇 基础医学(可授医学...
    • 13 篇 临床医学
    • 8 篇 药学(可授医学、理...
    • 6 篇 公共卫生与预防医...
  • 9 篇 法学
    • 7 篇 社会学
  • 8 篇 文学
    • 6 篇 中国语言文学
    • 5 篇 外国语言文学
  • 6 篇 教育学
  • 5 篇 农学
  • 1 篇 经济学

主题

  • 47 篇 speech recogniti...
  • 31 篇 speech
  • 30 篇 training
  • 18 篇 acoustics
  • 14 篇 machine translat...
  • 13 篇 decoding
  • 12 篇 social networkin...
  • 12 篇 speaker recognit...
  • 11 篇 hidden markov mo...
  • 11 篇 computational mo...
  • 11 篇 semantics
  • 10 篇 conferences
  • 9 篇 speech processin...
  • 9 篇 computational li...
  • 9 篇 feature extracti...
  • 9 篇 embeddings
  • 8 篇 training data
  • 8 篇 natural language...
  • 8 篇 pipelines
  • 7 篇 lattices

机构

  • 88 篇 human language t...
  • 54 篇 human language t...
  • 43 篇 center for langu...
  • 21 篇 center for langu...
  • 20 篇 human language t...
  • 20 篇 human language t...
  • 18 篇 center for langu...
  • 15 篇 human language t...
  • 13 篇 center for langu...
  • 12 篇 human language t...
  • 11 篇 human language t...
  • 10 篇 johns hopkins un...
  • 9 篇 johns hopkins un...
  • 8 篇 human language t...
  • 7 篇 human language t...
  • 7 篇 department of co...
  • 7 篇 xiaomi corp.
  • 6 篇 computer and inf...
  • 6 篇 xiaomi corporati...
  • 6 篇 center for langu...

作者

  • 64 篇 dredze mark
  • 50 篇 khudanpur sanjee...
  • 43 篇 van durme benjam...
  • 30 篇 dehak najim
  • 27 篇 sanjeev khudanpu...
  • 21 篇 post matt
  • 20 篇 mcnamee paul
  • 20 篇 hermansky hynek
  • 20 篇 callison-burch c...
  • 19 篇 villalba jesús
  • 18 篇 povey daniel
  • 16 篇 duh kevin
  • 16 篇 mayfield james
  • 15 篇 zelasko piotr
  • 15 篇 daniel povey
  • 15 篇 watanabe shinji
  • 14 篇 wiesner matthew
  • 14 篇 andrews nicholas
  • 13 篇 paul michael j.
  • 13 篇 mccree alan

语言

  • 448 篇 英文
  • 9 篇 其他
检索条件"机构=Human Language Technology Center of Excellence and Center for Language and Speech Processing"
457 条 记 录,以下是41-50 订阅
排序:
BLIND SIGNAL DEREVERBERATION FOR MACHINE speech RECOGNITION
arXiv
收藏 引用
arXiv 2022年
作者: Sadhu, Samik Hermansky, Hynek Center for Language and Speech Processing Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States
We present a method to remove unknown convolutive noise introduced to speech by reverberations of recording environments, utilizing some amount of training speech data from the reverberant environment, and any availab... 详细信息
来源: 评论
IMPORTANCE OF DIFFERENT TEMPORAL MODULATIONS OF speech: A TALE OF TWO PERSPECTIVES
arXiv
收藏 引用
arXiv 2022年
作者: Sadhu, Samik Hermansky, Hynek Center for Language and Speech Processing Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States
How important are different temporal speech modulations for speech recognition? We answer this question from two complementary perspectives. Firstly, we quantify the amount of phonetic information in the modulation sp... 详细信息
来源: 评论
Complex Frequency Domain Linear Prediction: A Tool to Compute Modulation Spectrum of speech
arXiv
收藏 引用
arXiv 2022年
作者: Sadhu, Samik Hermansky, Hynek Center for Language and Speech Processing Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States
Conventional Frequency Domain Linear Prediction (FDLP) technique models the squared Hilbert envelope of speech with varied degrees of approximation which can be sampled at the required frame rate and used as features ... 详细信息
来源: 评论
Contextualization with SPLADE for High Recall Retrieval
arXiv
收藏 引用
arXiv 2024年
作者: Yang, Eugene Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD United States
High Recall Retrieval (HRR), such as eDiscovery and medical systematic review, is a search problem that optimizes the cost of retrieving most relevant documents in a given collection. Iterative approaches, such as ite...
来源: 评论
Extending Translate-Train for ColBERT-X to African language CLIR
arXiv
收藏 引用
arXiv 2024年
作者: Yang, Eugene Lawrie, Dawn J. McNamee, Paul Mayfield, James Human Language Technology Center of Excellence Johns Hopkins University BaltimoreMD United States
This paper describes the submission runs from the HLTCOE team at the CIRAL CLIR tasks for African languages at FIRE 2023. Our submissions use machine translation models to translate the documents and the training pass... 详细信息
来源: 评论
ACOUSTIC MODELING FOR OVERLAPPING speech RECOGNITION: JHU CHIME-5 CHALLENGE SYSTEM
arXiv
收藏 引用
arXiv 2024年
作者: Manohar, Vimal Chen, Szu-Jui Wang, Zhiqi Fujita, Yusuke Watanabe, Shinji Khudanpur, Sanjeev Center for Language and Speech Processing Johns Hopkins University BaltimoreMD21218 United States Human Language Technology Center Of Excellence Johns Hopkins University BaltimoreMD21218 United States Hitachi Ltd. Research & Development Group Kokubunji-shi Tokyo Japan
This paper summarizes our acoustic modeling efforts in the Johns Hopkins University speech recognition system for the CHiME-5 challenge to recognize highly-overlapped dinner party speech recorded by multiple microphon... 详细信息
来源: 评论
DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model
arXiv
收藏 引用
arXiv 2023年
作者: Wang, Helin Thebaud, Thomas Villalba, Jesús Sydnor, Myra Lammers, Becky Dehak, Najim Moro-Velazquez, Laureano Center for Language and Speech Processing Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States Department of Physical Medicine and Rehabilitation Johns Hopkins University School of Medicine United States
We present a novel typical-to-atypical voice conversion approach (DuTa-VC), which (i) can be trained with nonparallel data (ii) first introduces diffusion probabilistic model (iii) preserves the target speaker identit... 详细信息
来源: 评论
MultiVENT: Multilingual Videos of Events with Aligned Natural Text
arXiv
收藏 引用
arXiv 2023年
作者: Sanders, Kate Etter, David Kriz, Reno Van Durme, Benjamin Johns Hopkins University Human Language Technology Center of Excellence United States
Everyday news coverage has shifted from traditional broadcasts towards a wide range of presentation formats such as first-hand, unedited video footage. Datasets that reflect the diverse array of multimodal, multilingu...
来源: 评论
Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling
Improving Neural Diarization through Speaker Attribute Attra...
收藏 引用
International Conference on Acoustics, speech, and Signal processing (ICASSP)
作者: David Palzer Matthew Maciejewski Eric Fosler-Lussier Computer Science and Engineering The Ohio State University Human Language Technology Center of Excellence The Johns Hopkins University
In recent years, end-to-end approaches have made notable progress in addressing the challenge of speaker diarization, which involves segmenting and identifying speakers in multi-talker recordings. One such approach, E...
来源: 评论
Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?
Do Text-to-Text Multi-Task Learners Suffer from Task Conflic...
收藏 引用
2022 Findings of the Association for Computational Linguistics: EMNLP 2022
作者: Mueller, David Andrews, Nicholas Dredze, Mark Department of Computer Science Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States
Traditional multi-task learning architectures learn a single model across multiple tasks through a shared encoder followed by task-specific decoders. Learning these models often requires specialized training algorithm... 详细信息
来源: 评论