咨询与建议

限定检索结果

文献类型

  • 10 篇 会议
  • 5 篇 期刊文献
  • 1 篇 学位论文

馆藏范围

  • 16 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 14 篇 工学
    • 12 篇 计算机科学与技术...
    • 6 篇 电气工程
    • 1 篇 交通运输工程
    • 1 篇 软件工程
    • 1 篇 安全科学与工程
  • 3 篇 理学
    • 3 篇 物理学
  • 2 篇 文学
    • 2 篇 外国语言文学
  • 1 篇 法学
    • 1 篇 社会学
  • 1 篇 医学
    • 1 篇 公共卫生与预防医...
  • 1 篇 管理学
    • 1 篇 管理科学与工程(可...

主题

  • 16 篇 encoder-decoder ...
  • 2 篇 deep learning
  • 2 篇 image segmentati...
  • 2 篇 listen attend sp...
  • 2 篇 automatic speech...
  • 2 篇 attention
  • 1 篇 panoptic segment...
  • 1 篇 multi-agent coll...
  • 1 篇 machine translat...
  • 1 篇 alpha matting
  • 1 篇 semantic segment...
  • 1 篇 ensemble learnin...
  • 1 篇 generative error...
  • 1 篇 post-asr error c...
  • 1 篇 generative adver...
  • 1 篇 long short-term ...
  • 1 篇 computer archite...
  • 1 篇 real-time safety...
  • 1 篇 failure predicti...
  • 1 篇 transfer learnin...

机构

  • 2 篇 flipkart bengalu...
  • 1 篇 samsung r&d inst...
  • 1 篇 univ waterloo wa...
  • 1 篇 but brno czech r...
  • 1 篇 flipkart
  • 1 篇 univ oxford oxfo...
  • 1 篇 harbin inst tech...
  • 1 篇 australian natl ...
  • 1 篇 snapchat machine...
  • 1 篇 univ essex csee ...
  • 1 篇 rembrand inc pal...
  • 1 篇 acad sinica taiw...
  • 1 篇 univ santiago de...
  • 1 篇 univ extremadura...
  • 1 篇 huawei san diego...
  • 1 篇 meta platforms i...
  • 1 篇 vit univ sch ele...
  • 1 篇 univ edinburgh s...
  • 1 篇 vanderbilt univ ...
  • 1 篇 univ calif los a...

作者

  • 2 篇 joshi raviraj
  • 1 篇 kothandaraman mo...
  • 1 篇 livescu karen
  • 1 篇 dalmia siddharth
  • 1 篇 mohapatra rohan
  • 1 篇 garera nikesh
  • 1 篇 schwarz patrick
  • 1 篇 kamper herman
  • 1 篇 scicchitano fran...
  • 1 篇 kannan venkatesh...
  • 1 篇 tsao yu
  • 1 篇 raghu srivatsav
  • 1 篇 zheng lai
  • 1 篇 lopez adam
  • 1 篇 mohamed abdelrah...
  • 1 篇 besacier laurent
  • 1 篇 goldwater sharon
  • 1 篇 coursey austin
  • 1 篇 hu zhenlin
  • 1 篇 salerno valerio ...

语言

  • 16 篇 英文
检索条件"主题词=Encoder-Decoder Models"
16 条 记 录,以下是11-20 订阅
排序:
Attention based end to end Speech Recognition for Voice Search in Hindi and English  13
Attention based end to end Speech Recognition for Voice Sear...
收藏 引用
Proceedings of the 13th annual meeting of the Forum for Information Retrieval Evaluation
作者: Joshi, Raviraj Kannan, Venkateshan Flipkart Bengaluru India
We describe here our work with automatic speech recognition (ASR) in the context of voice search functionality on the Flipkart e-Commerce platform. Starting with the deep learning architecture of Listen-Attend-Spell (... 详细信息
来源: 评论
RELAXED ATTENTION: A SIMPLE METHOD TO BOOST PERFORMANCE OF END-TO-END AUTOMATIC SPEECH RECOGNITION
RELAXED ATTENTION: A SIMPLE METHOD TO BOOST PERFORMANCE OF E...
收藏 引用
IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
作者: Lohrenz, Timo Schwarz, Patrick Li, Zhengyang Fingscheidt, Tim Tech Univ Carolo Wilhelmina Braunschweig Inst Commun Technol Schlcinitzstr 22 D-38106 Braunschweig Germany
Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks. Addressing overconfidence in such models, in this paper we int... 详细信息
来源: 评论
Attention based end to end Speech Recognition for Voice Search in Hindi and English  21
Attention based end to end Speech Recognition for Voice Sear...
收藏 引用
Proceedings of the 13th Annual Meeting of the Forum for Information Retrieval Evaluation
作者: Raviraj Joshi Venkateshan Kannan Flipkart India
We describe here our work with automatic speech recognition (ASR) in the context of voice search functionality on the Flipkart e-Commerce platform. Starting with the deep learning architecture of Listen-Attend-Spell (... 详细信息
来源: 评论
Deep Autoencoder Ensembles for Anomaly Detection on Blockchain  25th
Deep Autoencoder Ensembles for Anomaly Detection on Blockcha...
收藏 引用
25th International Symposium on Methodologies for Intelligent Systems (ISMIS)
作者: Scicchitano, Francesco Liguori, Angelica Guarascio, Massimo Ritacco, Ettore Manco, Giuseppe ICAR CNR Via P Bucci 8-9c Arcavacata Di Rende Italy
Distributed Ledger technologies are becoming a standard for the management of online transactions, mainly due to their capability to ensure data privacy, trustworthiness and security. Still, they are not immune to sec... 详细信息
来源: 评论
Low-Resource Speech-to-Text Translation  19
Low-Resource Speech-to-Text Translation
收藏 引用
19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018)
作者: Bansal, Sameer Kamper, Herman Livescu, Karen Lopez, Adam Goldwater, Sharon Univ Edinburgh Sch Informat Edinburgh Midlothian Scotland Stellenbosch Univ Stellenbosch South Africa Toyota Technol Inst Chicago IL USA
Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts neede... 详细信息
来源: 评论
Unsupervised Word Segmentation from Speech with Attention  19
Unsupervised Word Segmentation from Speech with Attention
收藏 引用
19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018)
作者: Godard, Pierre Boito, Marcely Zanon Ondel, Lucas Berard, Alexandre Yvon, Francois Villavicencio, Aline Besacier, Laurent Univ Paris Saclay CNRS LIMSI Orsay France UGA CNRS INRIA LIGG INP Grenoble France BUT Brno Czech Republic Univ Essex CSEE Colchester Essex England Univ Lille CRISTAL Lille France
We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodol... 详细信息
来源: 评论