• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.5
• /
• pp.2402-2409
• /
• 2011

The voice has distinguishable acoustic properties of speaker as well as transmitting information. The speaker recognition is the method to figures out who speaks the words through acoustic differences between speakers. The speaker recognition is roughly divided two kinds of categories: speaker verification and identification. The speaker verification is the method which verifies speaker himself based on only one's voice. Otherwise, the speaker identification is the method to find speaker by searching most similar model in the database previously consisted of multiple subordinate sentences. This paper composes feature vector from extracting MFCC coefficients and uses the dynamic time warping algorithm to compare the similarity between features. In order to describe common characteristic based on phonological features of spoken words, two subordinate sentences for each speaker are used as the training data. Thus, it is possible to identify the speaker who didn't say the same word which is previously stored in the database.

• Journal of Digital Convergence
• /
• v.11 no.9
• /
• pp.153-158
• /
• 2013

Target learning model is not recognized in this category or not classified clearly failed to determine if the vocabulary recognition is reduced. Form of classification learning model is changed or a new learning model is added to the recognition decision tree structure of the model should be changed to a structural problem. In order to solve these problems, a decision tree learning model for classification learning algorithm is proposed. Phonological phenomenon reflected sound enough to configure the database to ensure learning a decision tree learning model for classifying method was used. In this study, the indoor environment-dependent recognition and vocabulary words for the experimental results independent recognition vocabulary of the indoor environment-dependent recognition performance of 98.3% in the experiment showed, vocabulary independent recognition performance of 98.4% in the experiment shown.

• Atmosphere
• /
• v.25 no.4
• /
• pp.693-706
• /
• 2015

A shift of first fowering date (FFD) of spring blossoms (cherry, peach and pear) over the northest Asia under global warming is investiaged using dynamically downscaled daily temperature data with 12.5 km resolution. For the study, we obatained gridded daily data with Historical (1981~2010), and Representative Concentration Pathway (RCP) (2021~2100) 4.5 and 8.5 scenarios which were produced by WRFv3.4 in conjunction with HadGEM2-AO. A change on FFDs in 21st century is estimated by applying daily outputs of WRFv3.4 to DTS phonological model. Prior to projection on future climate, the performances of both WRFv3.4 and DTS models are evaluated using spatial distribution of climatology and SCR diagram (Normalized standard deviation-Pattern correlation coefficient-Root mean square difference). According to the result, WRFv3.4 and DTS models well simulated a feature of the terrain following characteristics and a general pattern of observation with a marigin of $1.4^{\circ}C$ and 5~6 days. The analysis reveals a projected advance in FFDs of cherry, peach and pear over the northeast Asia by 2100 of 15.4 days (9.4 days). 16.9 days (10.4 days) and 15.2 days (9.5 days), respectively, compared to the Historical simulation due to a increasing early spring (Februrary to April) temperature of about $4.9^{\circ}C$ ($2.9^{\circ}C$) under the RCP 8.5 (RCP 4.5) scenarios. This indicates that the current flowering of the cherry, peach and pear over analysis area in middle or end of April is expected to start blooming in early or middle of April, at the end of this century. The present study shows the dynamically downscaled daily data with high-resolution is helpeful in offering various useful information to end-users as well as in understanding regional climate change.