• 말소리와 음성과학
• /
• 제11권2호
• /
• pp.1-13
• /
• 2019

This study explored the relationship between accurate vowel production and proficiency levels in L2 English produced by Korean EFL adult learners. To this end, nine English vowels /i, ɪ, ɛ, æ, ʌ, ɔ, ɑ, ʊ, u/ were selected and adjacent vowels paired up (e.g., /i/-/ɪ/, /u/-/ʊ/, /ɛ/-/æ/, /ʌ/-/ɔ/, /ɔ/-/ɑ/). The spectral features of the pairs were measured instrumentally, namely F1 (indicating tongue height) and F2 (indicating tongue backness). Meanwhile, the durations as well as spectral features of the tense and lax counterparts in /i/-/ɪ/ and /u/-/ʊ/ were measured, as both temporal and spectral features are important in distinguishing them. The findings of this study confirm that higher-rated speakers were better able to distinguish the contrasts in the front vowel pairs /i/-/ɪ/ and /ɛ/-/æ/ than lower-rated learners, but in the central and back vowel pairs /u/-/ʊ/and /ʌ/-/ɔ/ (though not /ɔ/-/ɑ/), Korean EFL learners generally showed difficulty distinguishing adjacent vowels with spectral cues. On the other hand, the durations of the tense and lax vowels showed that the lower-rated speakers were less able to use the temporal feature to differentiate tense vowels from their lax counterparts, unlike previous studies that found that in general Korean learners depend excessively on the temporal cue to distinguish tense and lax vowels.

• 말소리와 음성과학
• /
• 제6권3호
• /
• pp.91-99
• /
• 2014

Although it is well documented that patients with cochlear implant experience hearing difficulties when processing their first language, very little is known whether or not and to what extent cochlear implant patients recognize segments in a second language. This preliminary study examines how Korean learners of English identify English segments in a normal hearing and cochlear implant simulation conditions. Participants heard English vowels and consonants in the following three conditions: normal hearing condition, 12-channel noise vocoding with 0mm spectral shift, and 12-channel noise vocoding with 3mm spectral shift. Results confirmed that nonnative listeners could also retrieve spectral information from vocoded speech signal, as they recognized vowel features fairly accurately despite the vocoding. In contrast, the intelligibility of manner and place features of consonants was significantly decreased by vocoding. In addition, we found that spectral shift affected listeners' vowel recognition, probably because information regarding F1 is diminished by spectral shifting. Results suggest that patients with cochlear implant and normal hearing second language learners would experience different patterns of listening errors when processing their second language(s).

• 한국음향학회지
• /
• 제29권4호
• /
• pp.265-269
• /
• 2010

본 논문에서는 새로운 형태의 스펙트럼 특징인 스펙트럼 대비 MFCC (SCMFCC)를 제안하고 음악 장르 분류 성능을 분석하였다. 음악 장르 분류를 위해서는 장르 간의 차이를 두드러지게 할 수 있는 특징을 사용해야 하므로, 음악의 화음 구조 및 강약을 잘 표현하는 스펙트럼 대비 특징들이 관심을 받아왔다. 본 논문에서 제안된 SCMFCC는 멜 켑스트럼 상에서 스펙트럼의 대비를 이용하여 기존의 MFCC를 음악 분류에 적합하도록 변형했다. 널리 사용되고 있는 음악 장르 데이터베이스에서 실험을 수행하여, 제안된 SCMFCC 특징의 음악 장르 분류 성능을 기존의 다른 특징들과 비교하였다.

• ETRI Journal
• /
• 제36권3호
• /
• pp.514-517
• /
• 2014

In this paper, alternative dynamic features for speech recognition are proposed. The goal of this work is to improve speech recognition accuracy by deriving the representation of distinctive dynamic characteristics from a speech spectrum. This work was inspired by two temporal dynamics of a speech signal. One is the highly non-stationary nature of speech, and the other is the inter-frame change of a speech spectrum. We adopt the use of a sub-frame spectrum analyzer to capture very rapid spectral changes within a speech analysis frame. In addition, we attempt to measure spectral fluctuations of a more complex manner as opposed to traditional dynamic features such as delta or double-delta. To evaluate the proposed features, speech recognition tests over smartphone environments were conducted. The experimental results show that the feature streams simply combined with the proposed features are effective for an improvement in the recognition accuracy of a hidden Markov model-based speech recognizer.

• International Journal of Computer Science & Network Security
• /
• 제23권3호
• /
• pp.177-186
• /
• 2023

Hyperspectral imaging technology is one of the most efficient and fast-growing technologies in recent years. Hyperspectral image (HSI) comprises contiguous spectral bands for every pixel that is used to detect the object with significant accuracy and details. HSI contains high dimensionality of spectral information which is not easy to classify every pixel. To confront the problem, we propose a novel RGB channel Assimilation for classification methods. The color features are extracted by using chromaticity computation. Additionally, this work discusses the classification of hyperspectral image based on Domain Transform Interpolated Convolution Filter (DTICF) and 3D-CNN with Bi-directional-Long Short Term Memory (Bi-LSTM). There are three steps for the proposed techniques: First, HSI data is converted to RGB images with spatial features. Before using the DTICF, the RGB images of HSI and patch of the input image from raw HSI are integrated. Afterward, the pair features of spectral and spatial are excerpted using DTICF from integrated HSI. Those obtained spatial and spectral features are finally given into the designed 3D-CNN with Bi-LSTM framework. In the second step, the excerpted color features are classified by 2D-CNN. The probabilistic classification map of 3D-CNN-Bi-LSTM, and 2D-CNN are fused. In the last step, additionally, Markov Random Field (MRF) is utilized for improving the fused probabilistic classification map efficiently. Based on the experimental results, two different hyperspectral images prove that novel RGB channel assimilation of DTICF-3D-CNN-Bi-LSTM approach is more important and provides good classification results compared to other classification approaches.

• 대한약학회:학술대회논문집
• /
• 대한약학회 2002년도 Proceedings of the Convention of the Pharmaceutical Society of Korea Vol.2
• /
• pp.402.2-402.2
• /
• 2002

An algorithm for finding the best regression models has been developed using NIR spectral data. In cases of regression analysis for quantitation with NIR spectral data, it is very critical to find essential features from the spectral data. This task was accessed in two ways. The first one was to use all-possible combinations of varibles (wavelengths). Correlation coefficients at each spectral points were calculated to get initial set of variables and all of the possible combinations of variable sets were tested with SEC. SEP and/or $R^2$. (omitted)

• 대한원격탐사학회지
• /
• 제35권4호
• /
• pp.561-571
• /
• 2019

In this paper, we analyze the effect of the representative spectral indices, normalized difference vegetation index (NDVI), normalized difference water index (NDWI) and normalized difference built-up index (NDBI) on classification accuracies of Landsat-8 OLI image.After creating these spectral index images, we propose five methods to select the spectral index images as classification features together with Landsat-8 OLI bands from 1 to 7. From the experiments we observed that when the spectral index image of NDVI or NDWI is used as one of the classification features together with the Landsat-8 OLI bands from 1 to 7, we can obtain higher overall accuracy and kappa coefficient than the method using only Landsat-8 OLI 7 bands. In contrast, the classification method, which selected only NDBI as classification feature together with Landsat-8 OLI 7 bands did not show the improvement in classification accuracies.

• Wind and Structures
• /
• 제1권3호
• /
• pp.203-223
• /
• 1998

This paper describes in detail the features of an extensive study on Spectral Density Functions (SDF's) of wind pressures acting on several low building roof geometries carried out in a boundary layer wind tunnel. Various spectral characteristics of wind pressures on roofs with emphasis on derivation of suitable analytical representation of spectra and determination of characteristic spectral shapes are shown. Standard spectral shapes associated with various zones of each roof and their parameters are provided. The established spectral parameters can be used to generate synthetic spectra adequate for the simulation of wind pressure fluctuations on building surfaces in a generic fashion.

• Current Optics and Photonics
• /
• 제5권5호
• /
• pp.562-575
• /
• 2021

As a new type of spectrometer, that based on filters with different transmittance features attracts a lot of attention for its advantages such as small-size, low cost, and simple optical structure. It uses post-processing algorithms to achieve target spectrum reconstruction; therefore, the performance of the spectrometer is severely affected by noise. The influence of noise on the spectral reconstruction results is studied in this paper, and suggestions for solving the spectral reconstruction problem under noisy conditions are given. We first list different spectral reconstruction methods, and through simulations demonstrate that these methods show unsatisfactory performance under noisy conditions. Then we propose to apply the gradient projection for sparse reconstruction (GRSR) algorithm to the spectral reconstruction method. Simulation results show that the proposed method can significantly reduce the influence of noise on the spectral reconstruction process. Meanwhile, the accuracy of the spectral reconstruction results is dramatically improved. Therefore, the practicality of the filter-based spectrometer will be enhanced.

• 산업경영시스템학회지
• /
• 제35권2호
• /
• pp.64-70
• /
• 2012

This paper presents a statistical analysis method for the selection of electroencephalogram (EEG) electrode positions and spectral features to recognize emotion, where emotional valence and arousal are classified into three and two levels, respectively. Ten experiments for a subject were performed under three categorized IAPS (International Affective Picture System) pictures, i.e., high valence and high arousal, medium valence and low arousal, and low valence and high arousal. The electroencephalogram was recorded from 12 sites according to the international 10~20 system referenced to Cz. The statistical analysis approach using ANOVA with Tukey's HSD is employed to identify statistically significant EEG electrode positions and spectral features in the emotion recognition.