咨询与建议

限定检索结果

文献类型

  • 3 篇 期刊文献
  • 1 篇 会议

馆藏范围

  • 4 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 4 篇 工学
    • 3 篇 电气工程
    • 1 篇 电子科学与技术(可...
    • 1 篇 信息与通信工程
    • 1 篇 计算机科学与技术...
    • 1 篇 船舶与海洋工程
  • 2 篇 理学
    • 2 篇 物理学

主题

  • 4 篇 attention-based ...
  • 2 篇 speech recogniti...
  • 1 篇 code-switching l...
  • 1 篇 adaptation
  • 1 篇 tuning
  • 1 篇 lstm
  • 1 篇 hidden markov mo...
  • 1 篇 hindi-english co...
  • 1 篇 transfer learnin...
  • 1 篇 end-to-end speec...
  • 1 篇 logic gates
  • 1 篇 sequence-to-sequ...
  • 1 篇 word-level and s...
  • 1 篇 predictive model...
  • 1 篇 decoding
  • 1 篇 speech synthesis
  • 1 篇 automatic speech...
  • 1 篇 online speech re...
  • 1 篇 bengali-english ...
  • 1 篇 data augmentatio...

机构

  • 1 篇 ntt corp ntt med...
  • 1 篇 kyoto univ grad ...
  • 1 篇 indian inst engn...
  • 1 篇 kyoto univ grad ...
  • 1 篇 seoul natl univ ...

作者

  • 2 篇 kawahara tatsuya
  • 2 篇 ueno sei
  • 2 篇 mimura masato
  • 2 篇 sakai shinsuke
  • 1 篇 bhowmick rajat s...
  • 1 篇 ganguli isha
  • 1 篇 cheon sung jun
  • 1 篇 kim nam soo
  • 1 篇 lee hyeonseung
  • 1 篇 aono yushi
  • 1 篇 sil jaya
  • 1 篇 yamaguchi yoshik...
  • 1 篇 kang woo hyun
  • 1 篇 moriya takafumi
  • 1 篇 kim hyeongju
  • 1 篇 shinohara yusuke

语言

  • 4 篇 英文
检索条件"主题词=Attention-based encoder-decoder model"
4 条 记 录,以下是1-10 订阅
排序:
Deep Insights of Erroneous Bengali-English Code-Mixed Bilingual Language
收藏 引用
IETE JOURNAL OF RESEARCH 2023年 第6期69卷 3334-3345页
作者: Ganguli, Isha Bhowmick, Rajat Subhra Sil, Jaya Indian Inst Engn Sci & Technol Dept Comp Sci & Technol Sibpur India
Code-switching, the combination of more than one language within a single utterance is popular in social media sites for informal communication, generating a huge amount of data, though not fully analysed for knowledg... 详细信息
来源: 评论
Gated Recurrent Context: Softmax-Free attention for Online encoder-decoder Speech Recognition
收藏 引用
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2021年 29卷 710-719页
作者: Lee, Hyeonseung Kang, Woo Hyun Cheon, Sung Jun Kim, Hyeongju Kim, Nam Soo Seoul Natl Univ Inst New Media & Commun Dept Elect & Comp Engn Seoul 08826 South Korea
Recently, attention-based encoder-decoder (AED) models have shown state-of-the-art performance in automatic speech recognition (ASR). As the original AED models with global attentions are not capable of online inferen... 详细信息
来源: 评论
Synthesizing waveform sequence-to-sequence to augment training data for sequence-to-sequence speech recognition
收藏 引用
ACOUSTICAL SCIENCE AND TECHNOLOGY 2021年 第6期42卷 333-343页
作者: Ueno, Sei Mimura, Masato Sakai, Shinsuke Kawahara, Tatsuya Kyoto Univ Grad Sch Informat Sakyo Ku Kyoto 6068501 Japan
Sequence-to-sequence (seq2seq) automatic speech recognition (ASR) recently achieves state-of-the-art performance with fast decoding and a simple architecture. On the other hand, it requires a large amount of training ... 详细信息
来源: 评论
encoder Transfer for attention-based Acoustic-to-word Speech Recognition  19
Encoder Transfer for Attention-based Acoustic-to-word Speech...
收藏 引用
19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018)
作者: Ueno, Sei Moriya, Takafumi Mimura, Masato Sakai, Shinsuke Shinohara, Yusuke Yamaguchi, Yoshikazu Aono, Yushi Kawahara, Tatsuya NTT Corp NTT Media Intelligence Labs Tokyo Japan Kyoto Univ Grad Sch Informat Sakyo Ku Kyoto Japan
Acoustic-to-word speech recognition based on attention-based encoder-decoder models achieves better accuracies with much lower latency than the conventional speech recognition systems. However, acoustic-to-word models... 详细信息
来源: 评论