期刊文献+

语音大数据信息处理架构及关键技术研究 被引量:6

Study of Audio Frequency Big Data Processing Architecture and Key Technology
下载PDF
导出
摘要 针对如何从音频信息中获得有商业价值的信息这一大数据研究的重要方向,首先分析了大数据的基础技术特性、涉及的技术,然后分析了语音识别的基本技术环节,最后结合大数据信息处理架构,给出了语音识别技术与大数据相结合的应用开发技术架构及应用流程。 As the major part of big data research, the audio frequency's value has not been discovered. The features of big data, and the automatic speech recognition (ASR) technology were studied, and the value was mined through the method that combined with the two technologies. Finally, the application development technical architecture and application process of audio frequency which combined with big data were given.
出处 《电信科学》 北大核心 2013年第11期1-5,共5页 Telecommunications Science
关键词 自然语言处理架构 大数据 自动语音识别 natural language processing architecture, big data, automatic speech recognition
  • 相关文献

参考文献7

二级参考文献89

  • 1钱跃良,林守勋,刘群,刘宏.2005年度863计划中文信息处理与智能人机接口技术评测回顾[J].中文信息学报,2006,20(B03):1-6. 被引量:4
  • 2付强,Peter Murphy,颜永红.一种基于联合源-滤波器模型优化的语音声门源模型估计方法[J].电子学报,2007,35(5):982-986. 被引量:3
  • 3Zhang, B., S. Matsoukas and R. Schwartz. Discrimina tively trained region dependent teature transforms for speech recognition [C]// Proc. ICASSP, Vol. 1-13, 2006: 313-316.
  • 4Beyerlein, P., et al., Large vocabulary continuous speech recognition of Broadcast News - The Philips/ RWTH approach[J]. Speech Communication, 2002, 37(1-2): 109- 131.
  • 5Hain, T., et al., Automatic transcription of conversational telephone speech [C]// IEEE Transactions on Speech and Audio Processing, 2005, 13(6): 1173-1185.
  • 6Zhang, B. and S. Matsoukas, Minimum phoneme error based heteroscedastic linear discriminant analy sis for speech recognition[C]// Proc. ICASSP, Vol. 1-5, 2005: 1925-1928.
  • 7Hirsimaki, T., et al., Unlimited vocabulary speech recognition with morph language models applied to Finnish[J]. Computer Speech and Language, 2006, 20(4) : 515-541.
  • 8Odell, J.J., The Use of Context in Large Vocabulary Speech Recognition[D]. 1995, University of Cambridge :Cambridge
  • 9Young, S.J., J.J. Odell, and P. C. Woodland. Tree-Based State Tying for High Accuracy Modelling [C]// Proceedings ARPA Workshop on Human Language Technology. 1994.
  • 10Xu, B., et al., Integrating tone information in continuous Mandarin recognition[C]// Proc. ISSPIS, 1999.

共引文献160

同被引文献28

引证文献6

二级引证文献48

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部