咨询与建议

限定检索结果

文献类型

  • 267 篇 会议
  • 155 篇 期刊文献

馆藏范围

  • 422 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 282 篇 工学
    • 184 篇 计算机科学与技术...
    • 164 篇 软件工程
    • 111 篇 信息与通信工程
    • 28 篇 生物工程
    • 27 篇 电子科学与技术(可...
    • 24 篇 电气工程
    • 23 篇 控制科学与工程
    • 21 篇 仪器科学与技术
    • 19 篇 化学工程与技术
    • 11 篇 机械工程
    • 8 篇 生物医学工程(可授...
    • 6 篇 光学工程
    • 5 篇 建筑学
    • 4 篇 土木工程
    • 3 篇 材料科学与工程(可...
  • 176 篇 理学
    • 137 篇 物理学
    • 56 篇 数学
    • 31 篇 生物学
    • 19 篇 化学
    • 16 篇 统计学(可授理学、...
    • 8 篇 系统科学
  • 44 篇 管理学
    • 37 篇 图书情报与档案管...
    • 7 篇 管理科学与工程(可...
  • 11 篇 法学
    • 11 篇 社会学
  • 8 篇 医学
    • 7 篇 临床医学
    • 6 篇 基础医学(可授医学...
    • 5 篇 药学(可授医学、理...
  • 7 篇 文学
    • 6 篇 中国语言文学
    • 5 篇 外国语言文学
  • 4 篇 教育学
    • 4 篇 教育学
  • 3 篇 农学
  • 2 篇 艺术学

主题

  • 59 篇 speech recogniti...
  • 52 篇 training
  • 33 篇 acoustics
  • 31 篇 speech
  • 20 篇 speech processin...
  • 19 篇 feature extracti...
  • 18 篇 hidden markov mo...
  • 18 篇 signal processin...
  • 16 篇 computational mo...
  • 15 篇 conferences
  • 14 篇 speech enhanceme...
  • 13 篇 predictive model...
  • 13 篇 decoding
  • 12 篇 machine translat...
  • 11 篇 speech synthesis
  • 10 篇 training data
  • 10 篇 neural networks
  • 10 篇 data models
  • 9 篇 transformers
  • 9 篇 self-supervised ...

机构

  • 71 篇 national enginee...
  • 51 篇 human language t...
  • 46 篇 center for langu...
  • 31 篇 human language t...
  • 21 篇 center for langu...
  • 21 篇 center for langu...
  • 13 篇 center for langu...
  • 11 篇 iflytek research
  • 10 篇 center for langu...
  • 9 篇 ict cluster sing...
  • 9 篇 human language t...
  • 8 篇 national enginee...
  • 8 篇 center for langu...
  • 8 篇 human language t...
  • 7 篇 center for langu...
  • 7 篇 human language t...
  • 7 篇 university of sc...
  • 7 篇 xiaomi corp.
  • 6 篇 university of sc...
  • 6 篇 state key labora...

作者

  • 49 篇 ling zhen-hua
  • 47 篇 khudanpur sanjee...
  • 35 篇 dehak najim
  • 32 篇 ai yang
  • 29 篇 sanjeev khudanpu...
  • 23 篇 zhen-hua ling
  • 23 篇 dredze mark
  • 19 篇 povey daniel
  • 19 篇 yang ai
  • 18 篇 villalba jesús
  • 18 篇 van durme benjam...
  • 18 篇 daniel povey
  • 17 篇 post matt
  • 16 篇 hermansky hynek
  • 16 篇 lu ye-xin
  • 15 篇 zelasko piotr
  • 14 篇 du hui-peng
  • 13 篇 raj desh
  • 13 篇 gu jia-chen
  • 13 篇 watanabe shinji

语言

  • 344 篇 英文
  • 78 篇 其他
  • 2 篇 中文
检索条件"机构=Center for Language and Speech Processing & Human Language Technology"
422 条 记 录,以下是71-80 订阅
排序:
Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection
Prototype based Masked Audio Model for Self-Supervised Learn...
收藏 引用
International Conference on Acoustics, speech, and Signal processing (ICASSP)
作者: Pengfei Cai Yan Song Nan Jiang Qing Gu Ian McLoughlin National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China China ICT Cluster Singapore Institute of Technology Singapore
A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on la... 详细信息
来源: 评论
Regularizing Contrastive Predictive Coding for speech Applications
arXiv
收藏 引用
arXiv 2023年
作者: Bhati, Saurabhchand Villalba, Jesús Zelasko, Piotr Moro-Velazquez, Laureano Dehak, Najim Center for Language and Speech Processing Johns Hopkins University United States Human Language Technology Center of Excellence Johns Hopkins University United States Meaning.Team Inc United States
Self-supervised methods such as Contrastive predictive Coding (CPC) have greatly improved the quality of the unsupervised representations. These representations significantly reduce the amount of labeled data needed f... 详细信息
来源: 评论
Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-speech Synthesis
Incremental Disentanglement for Environment-Aware Zero-Shot ...
收藏 引用
International Conference on Acoustics, speech, and Signal processing (ICASSP)
作者: Ye-Xin Lu Hui-Peng Du Zheng-Yan Sheng Yang Ai Zhen-Hua Ling National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei P. R. China
This paper proposes an Incremental Disentanglement-based Environment-Aware zero-shot text-to-speech (TTS) method, dubbed IDEA-TTS, that can synthesize speech for unseen speakers while preserving the acoustic character... 详细信息
来源: 评论
Towards robust one-shot voice conversion with cycle phonetic posteriorgrams and multi-scale speaker representations  24
Towards robust one-shot voice conversion with cycle phonetic...
收藏 引用
24th International Congress on Acoustics, ICA 2022
作者: Chen, Yannian Liu, Lijuan Hu, Yajun Ling, Zhenhua National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China China IFLYTEK Research IFLYTEK Co. Ltd. China
One-shot voice conversion (VC) aims to convert the voice across arbitrary speakers even unseen during training, with only one reference utterance from the target speaker. It is still a challenging task as both content... 详细信息
来源: 评论
Document-Level Machine Translation with Effective Batch-Level Context Representation
Document-Level Machine Translation with Effective Batch-Leve...
收藏 引用
International Joint Conference on Neural Networks (IJCNN)
作者: Kang Zhong Jie Zhang Wu Guo National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP) University of Science and Technology of China (USTC) Hefei China
It is critical to provide inter-sentential context for document-level neural machine translation (DocNMT) to achieve higher-quality translations. As the document-level information is naturally preserved in mini-batche... 详细信息
来源: 评论
Multiscale Matching Driven by Cross-Modal Similarity Consistency for Audio-Text Retrieval
Multiscale Matching Driven by Cross-Modal Similarity Consist...
收藏 引用
International Conference on Acoustics, speech, and Signal processing (ICASSP)
作者: Qian Wang Jia-Chen Gu Zhen-Hua Ling National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei P.R.China
Audio-text retrieval (ATR), which retrieves a relevant caption given an audio clip (A2T) and vice versa (T2A), has recently attracted much research attention. Existing methods typically aggregate information from each...
来源: 评论
PNP-RKD: A Positive-Negative Pair based Relational Knowledge Distillation Method for Cross-Domain Speaker Verification
PNP-RKD: A Positive-Negative Pair based Relational Knowledge...
收藏 引用
International Conference on Acoustics, speech, and Signal processing (ICASSP)
作者: Qing Gu Yan Song Nan Jiang Pengfei Cai Ian McLoughlin National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China ICT Cluster Singapore Institute of Technology Singapore
Existing deep embedding learning based speaker verification (SV) methods suffer from performance degradation under domain shift conditions. This can be alleviated through unsupervised domain adaptation (UDA) technique... 详细信息
来源: 评论
Considering Temporal Connection between Turns for Conversational speech Synthesis
Considering Temporal Connection between Turns for Conversati...
收藏 引用
International Conference on Acoustics, speech, and Signal processing (ICASSP)
作者: Kangdi Mei Zhaoci Liu Huipeng Du Hengyu Li Yang Ai Liping Chen Zhenhua Ling National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei P.R. China
Conversational speech synthesis aims to synthesize speech of an individual speaker based on history conversation. However, most studies in conversational speech synthesis only focus on the synthesis performance of the...
来源: 评论
Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection
arXiv
收藏 引用
arXiv 2024年
作者: Cai, Pengfei Song, Yan Jiang, Nan Gu, Qing McLoughlin, Ian National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China China ICT Cluster Singapore Institute of Technology Singapore
A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on la... 详细信息
来源: 评论
Clustering Unsupervised Representations as Defense Against Poisoning Attacks on speech Commands Classification System
Clustering Unsupervised Representations as Defense Against P...
收藏 引用
IEEE Workshop on Automatic speech Recognition and Understanding
作者: Thomas Thebaud Sonal Joshi Henry Li Martin Sustek Jesús Villalba Sanjeev Khudanpur Najim Dehak Center for Language and Speech Processing Johns Hopkins University USA Faculty of Information Technology Brno University of Technology Czechia
Poisoning attacks entail attackers intentionally tampering with training data. In this paper, we consider a dirty-label poisoning attack scenario on a speech commands classification system. The threat model assumes th...
来源: 评论