Real-time frequency-based noise-robust Automatic Speech Recognition using Multi-Nets Artificial Neural Networks A multi-views multi-learners approach.pdfVIP

下载本文档

3
0
约 9页
2017-03-16 发布于天津
举报
版权申诉

Real-time frequency-based noise-robust Automatic Speech Recognition using Multi-Nets Artificial Neural Networks A multi-views multi-learners approach.pdf

1、本文档共9页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Real-time frequency-based noise-robust Automatic Speech Recognition using Multi-Nets Artificial Neural Networks A multi-views multi-learners approach.pdf

Neurocomputing 129 (2014) 199–207 Contents lists available at ScienceDirect Neurocomputing journal homepage: /locate/neucom Real-time frequency-based noise-robust Automatic Speech Recognition using Multi-Nets Arti?cial Neural Networks: A multi-views multi-learners approach Seyed Reza Shahamiri n, Siti Salwah Binti Salim 1 Department of Software Engineering, Faculty of Computer Science and Information Technology, University of Malaya, 50603 Lembah Pantai, Kuala Lumpur, Malaysia article info Article history: Received 21 May 2013 Received in revised form 15 August 2013 Accepted 27 September 2013 Communicated by Shiliang Sun Available online 24 October 2013 Keywords: Multiple-views multiple-learners Automatic Speech Recognition Arti?cial neural network Noise robustness Frequency-based noise abstract Automatic Speech Recognition (ASR) is a technology for identifying uttered word(s) represented as an acoustic signal. However, one of the important aspects of a noise-robust ASR system is its ability to recognise speech accurately in noisy conditions. This paper studies the applications of Multi-Nets Arti?cial Neural Networks (M-N ANNs), a realisation of multiple-views multiple-learners approach, as Multi-Networks Speech Recognisers (M-NSRs) in providing a real-time, frequency-based noise-robust ASR model. M-NSRs de?ne speech features associated with each word as a different view and apply a standalone ANN as one of the learners to approximate that view; meanwhile, multiple-views singlelearner (MVSL) ANN-based speech recognisers employ only one ANN to memorise the features of the entire vocabulary. In this research, an M-NSR was provided and evaluated using unforeseen test data that were affected by white, brown, and pink noises; more speci?cally, 27 experiments were conducted on noisy speech to measure the accuracy and recognition rate of the proposed model. Furthermore, the results of the M-NSR were compared in detail with an MVSL ANN-based ASR system. The M-NSR recorded a