期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2015
卷号：4
期号：2
页码：571
DOI：10.15680/IJIRSET.2015.0402067
出版社：S&S Publications
摘要：Speech is the most innate and fastest means of communication between humans. Computers with theability to understand speech and speak with a human like voice are expected to contribute to the development of morenatural man-machine interface. For the analysis of speech signal we have carried out the recording of six childrenspeakers (3 male and 3 female) in Dogri language between the age group of 3-6 years. Harmonic plus noise modelHNM has been employed as the analysis-synthesis platform as it outperforms almost all models of speech production interms of important characteristics like naturalness, intelligibility, and pleasantness. PESQ method is used for evaluationof the quality of the speech synthesized from HNM. Mean and standard deviation (SD) is estimated for original andsynthesized speech. Effect of different proportion of voice part on the quality and intelligibility of speech signal ofchildren has been investigated at different levels of noise keeping noise part constant. Results suggest that the quality isquite poor at lower levels of voice part but increases gradually until the value of voice part is 50%. However as thevoice percentage is increased the quality remains constant afterwards (till v100%). Results suggest that the percentageof voice part plays an important part for the quality of speech. With no voice part the quality is quite poor. Further theresults prove that HNM is an excellent model for children speech. Also the worst and best speech quality is not samefor male and female children speakers.
