期刊文献+

基于听觉事件检测的汉语语音声韵切分 被引量:7

Segmentation of Chinese initials and finals based on auditory event detection
下载PDF
导出
摘要 提出了一种基于听觉事件检测的汉语声韵母切分方法。该方法首先使用耳蜗滤波器组对语音进行滤波,然后在每个频带上检测对应于能量突变的听觉事件,最后在不同频率范围对听觉事件进行融合以确定声韵母边界。实验结果表明,对8 kHz采样的干净语音切分准确率可达到88.9%;信噪比10 dB的语音切分准确率可达到82.9%以上。 This paper presents a segmentation method of Chinese initials and finals based on the detection of auditory events.According to this method,the voice should first of all be filtered by using the cochlear filter bank,and then the auditory events corresponding to energy mutation in each band are detected.Finally,the auditory events are integrated in different frequency ranges respectively to determine the boundaries of Chinese initials and finals.The experimental results show that with 8 kHz sampling frequency,the accuracy is 88.9%for clean speech and above 82.9%for noisy speech with the SNR of 10 dB.
出处 《声学学报》 EI CSCD 北大核心 2010年第6期701-707,共7页 Acta Acustica
基金 国家高技术研究发展(863)计划项目<海量语音识别综合处理系统>(2006AA01Z146)
  • 相关文献

参考文献9

二级参考文献32

  • 1陈韬,李昌立,莫福源.汉语孤立字全音节实时识别系统[J].声学学报,1993,18(3):161-171. 被引量:4
  • 2赵鹤呜,周旭东.一种新的听觉感知模型[J].电子科学学刊,1994,16(5):513-517. 被引量:4
  • 3潘凌云,孙达传,吴美朝.语音识别中基于语谱图的语音音素分割方法[J].杭州大学学报(自然科学版),1995,22(1):42-46. 被引量:7
  • 4齐士钤 张家禄.汉语普通话辅音音长分析[J].声学学报,1982,(1):8-13.
  • 5曹剑芬.现代语音基础知识[M].北京:人民教育出版社,1990..
  • 6秦勇.汉语超大词汇语音识别系统的研究与实现.中国科学院声学研究所博士论文[M].,1996..
  • 7Fant G 张家lu等(译).言语科学与言语技术[M].北京:商务印书馆,1994..
  • 8[1]Kumar K,Mullick S K.Nonlinear dynamical analysis of speech [J].J Acou stic Soc Amer,1996,100(1): 615-629.
  • 9[2]Maragos P.Fractal aspects of speech signals: dimension and interpolation [A].Proc IEEE Int Conf Acoust,Speech,Signal Proc [C].Piscataway,NJ: IEEE,1991.417-420.[3] Thomas T J.A fini te element model of fluid flow in the vocal tract [J].Comput Speech Lang,198 6,1: 131-151.
  • 10[3]Mandelbort B B.The Fractal Geometry of Nature [M].New York: Freeman,1982.

共引文献56

同被引文献82

  • 1栗学丽,丁慧,徐柏龄.基于熵函数的耳语音声韵分割法[J].声学学报,2005,30(1):69-75. 被引量:34
  • 2邝航宇,张军,韦岗.一种基于检测元音的孤立词端点检测算法[J].电声技术,2005,29(3):40-43. 被引量:5
  • 3李朝晖,迟惠生.听觉外周计算模型研究进展[J].声学学报,2006,31(5):449-465. 被引量:22
  • 4Lee Chin-Hui. From knowledge-ignorant to knowledge-rich modeling: A new speech research paradigm for next gen- eration automatic speech recognition. In: Proc. Of ICSLP Keynote speech, Jeju Island, Korea, 2004:213 216.
  • 5Toledano D T, Gomez L A H, Grande L V. Automatic phonetic segmentation. IEEE Transactions on A U- DIO SPEECH and LA NG UA GE Processing, 2005; 11 (6): 617-625.
  • 6Malfrere F, Dutiot T. High-quality speech synthesis for phonetic speech segmentation. In: Proc. Eurospeech'97, Rhodes, Greece, 1997:2631-2634.
  • 7Kuo J W, Wang H M. Minimum boundary error training for automatic phonetic segmentation. In: Proc. Of Interspeech, Pittsburgh, USA. 2006:1497-1500.
  • 8Nuo J W, Lo H Y, Wang H M. Improved HMM/SVM methods for automatic phoneme segmentation. In: Proc. of Interspeech, Antwerp, Belgium, 2007(2): 2057-2060.
  • 9Lo H Y, Wang H M. Phonetic boundary refinement using neural network . In: Proc. of ICASSP, Istanbul, Turkey, 2007:3438-3441.
  • 10van Santen J, Sproat R. High accuracy automatic segmentation. In: Proc. Eurospeech'99, Budapest, Hungary, 1999:2809-2812.

引证文献7

二级引证文献11

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