首页> 外文OA文献 >Latent Dirichlet Allocation Based Organisation of Broadcast Media Archives for Deep Neural Network Adaptation
【2h】

Latent Dirichlet Allocation Based Organisation of Broadcast Media Archives for Deep Neural Network Adaptation

机译:基于潜在Dirichlet分配的广播媒体档案深度神经网络自适应组织

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

This paper presents a new method for the discovery of latent domains in diverse speech data, for the use of adaptation of Deep Neural Networks (DNNs) for Automatic Speech Recognition. Our work focuses on transcription of multi-genre broadcast media, which is often only categorised broadly in terms of high level genres such as sports, news, documentary, etc. However, in terms of acoustic modelling these categories are coarse. Instead, it is expected that a mixture of latent domains can better represent the complex and diverse behaviours within a TV show, and therefore lead to better and more robust performance. We propose a new method, whereby these latent domains are discovered with Latent Dirichlet Allocation, in an unsupervised manner. These are used to adapt DNNs using the Unique Binary Code (UBIC) representation for the LDA domains. Experiments conducted on a set of BBC TV broadcasts, with more than 2,000 shows for training and 47 shows for testing, show that the use of LDA-UBIC DNNs reduces the error up to 13% relative compared to the baseline hybrid DNN models.udud
机译:本文提出了一种新方法,可用于发现多种语音数据中的潜在域,并利用深层神经网络(DNN)进行自动语音识别。我们的工作集中在多流媒体广播媒体的转录上,这些媒体通常仅按照体育,新闻,纪录片等高级别流媒体进行广泛分类。但是,在声学建模方面,这些类别比较粗糙。取而代之的是,预期潜在域的混合可以更好地表示电视节目中复杂多样的行为,从而带来更好,更强大的性能。我们提出了一种新的方法,通过这些方法可以在无监督的情况下通过潜在狄利克雷分配来发现这些潜在域。这些用于通过LDA域的唯一二进制码(UBIC)表示来适应DNN。在一组BBC电视广播上进行的实验(用于培训的2,000多个节目和用于测试的47个节目)显示,与基线混合DNN模型相比,LDA-UBIC DNN的使用最多可将错误减少13%。 ud ud

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号