.png){kind=icon}
返回
Multilingually trained bottleneck features in spoken language recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.csl.2017.06.008.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multilingual training of neural networks has proven to be simple yet effective way to deal with multilingual training corpora. It allows to use several resources to jointly train a language independent representation of features, which can be encoded into low dimensional feature set by embedding narrow bottleneck layer to the network. In this paper, we analyze such features on the task of spoken language recognition (SLR), focusing on practical aspects of training bottleneck networks and analyzing their integration in SLR. By comparing properties of mono and multilingual features we show the suitability of multilingual training for SLR. The state-of-the-art performance of these features is demonstrated on the NIST LRE09 database. (C) 2017 Elsevier Ltd. All rights reserved.
Keyword:
Multilingual training
Bottleneck features
Spoken language recognition
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
C
IF:
3.4
论文数:
1.5K
被引数:
2.6K
机构
引用论文
Universal attribute characterization of spoken languages for automatic spoken language recognition
.png){kind=icon}
PREAI
分享收藏The relationship between performance on the standardised field sobriety tests, driving performance and the level of Δ9-tetrahydrocannabinol (THC) in blood标准化现场清醒测试的性能，驾驶性能与血液中 Δ9-四氢大麻酚 (THC) 水平之间的关系
PREAI
分享收藏
Hymenolepis diminuta: Further characterization of the membrane-bound acid phosphatase activity associated with the brush border membrane of the tapeworm's tegumentHymenolepis diminuta：进一步表征与绦虫表皮刷状缘膜相关的膜结合酸性磷酸酶活性
PREAI
分享收藏分享收藏 没有更多内容
没有更多内容