咨询与建议

限定检索结果

文献类型

  • 3 篇 会议
  • 2 篇 期刊文献

馆藏范围

  • 5 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 5 篇 工学
    • 4 篇 计算机科学与技术...
    • 3 篇 控制科学与工程
    • 2 篇 软件工程
    • 1 篇 信息与通信工程
  • 2 篇 理学
    • 2 篇 数学
    • 2 篇 系统科学

主题

  • 5 篇 multi-stack deco...
  • 3 篇 search methods
  • 2 篇 viterbi beam sea...
  • 2 篇 probabilistic ca...
  • 2 篇 similarity measu...
  • 2 篇 speech recogniti...
  • 1 篇 stack decoding
  • 1 篇 phoneme grouping
  • 1 篇 segmental speech...
  • 1 篇 multi-pass searc...

机构

  • 2 篇 univ szeged h-67...
  • 2 篇 grad. school of ...
  • 1 篇 grad. school of ...
  • 1 篇 research group o...
  • 1 篇 department of in...
  • 1 篇 hungarian acad s...
  • 1 篇 hungarian acad s...
  • 1 篇 grad. school of ...

作者

  • 2 篇 kuniyoshi yasuo
  • 2 篇 harada tatsuya
  • 2 篇 ushiku yoshitaka
  • 1 篇 tóth lászló
  • 1 篇 kocsor andrás
  • 1 篇 kocsor a
  • 1 篇 gosztolya gabor
  • 1 篇 gosztolya g
  • 1 篇 gosztolya gábor
  • 1 篇 felföldi lászló
  • 1 篇 kocsor andras

语言

  • 5 篇 英文
检索条件"主题词=Multi-stack decoding"
5 条 记 录,以下是1-10 订阅
Understanding images with natural sentences  11
Understanding images with natural sentences
收藏 引用
19th ACM International Conference on multimedia ACM multimedia 2011, MM'11
作者: Ushiku, Yoshitaka Harada, Tatsuya Kuniyoshi, Yasuo Grad. School of Information Science and Technology University of Tokyo Japan Grad. School of Information Science and Technology University of Tokyo / JST PRESTO Japan
We propose a novel system which generates sentential captions for general images. For people to use numerous images effectively on the web, technologies must be able to explain image contents and must be capable of se... 详细信息
来源: 评论
Automatic sentence generation from images  11
Automatic sentence generation from images
收藏 引用
19th ACM International Conference on multimedia ACM multimedia 2011, MM'11
作者: Ushiku, Yoshitaka Harada, Tatsuya Kuniyoshi, Yasuo Grad. School of Information Science and Technology University of Tokyo Japan Grad. School of Information Science and Technology University of Tokyo JST PRESTO Japan
For the overwhelming amounts of multimedia used on the Web, methods of search and understanding with sentences are necessary. Representing the contents not only using labels but also using sentences including labels&#... 详细信息
来源: 评论
Improving the multi-stack decoding algorithm in a segment-based speech recognizer  16th
收藏 引用
16th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems
作者: Gosztolya, G Kocsor, A Hungarian Acad Sci Res Grp Artificial Intelligence H-6720 Szeged Hungary Univ Szeged H-6720 Szeged Hungary
During automatic speech recognition selecting the best hypothesis over a combinatorially huge hypothesis space is a very hard task, so selecting fast and efficient heuristics is a reasonable strategy. In this paper a ... 详细信息
来源: 评论
A Hierarchical Evaluation Methodology in Speech Recognition
收藏 引用
ACTA CYBERNETICA 2005年 第2期17卷 213-224页
作者: Gosztolya, Gabor Kocsor, Andras Hungarian Acad Sci Res Grp Artificial Intelligence Budapest Hungary Univ Szeged H-6720 Szeged Hungary
In speech recognition vast hypothesis spaces are generated, so the search methods used and their speedup techniques are both of great importance. One way of getting a speedup gain is to search in multiple steps. In th... 详细信息
来源: 评论
Various robust search methods in a Hungarian speech recognition system
收藏 引用
Acta Cybernetica 2003年 第2期16卷 229-240页
作者: Gosztolya, Gábor Kocsor, András Tóth, László Felföldi, László Research Group on Artificial Intell. Hungarian Academy of Sciences University of Szeged Aradi Vértanúk tere 1. H-6720 Szeged Hungary Department of Informatics University of Szeged Arpád tér 2. H-6720 Szeged Hungary
This work focuses on the search aspect of speech recognition. We describe some standard algorithms such as stack decoding, multi-stack decoding, the Viterbi beam search and an A* heuristic, then present improvements o... 详细信息
来源: 评论