• Speech Sciences
• /
• v.2
• /
• pp.125-134
• /
• 1997

Human beings can perceive various aspects of sound including loudness, pitch, length, and timber. Recently many studies were conducted to clarify complex auditory scales of the human ear. This study critically reviews some of these scales (decibel, sone, phon for loudness perception; mel and bark for pitch) and proposes to apply the scales to normalize acoustic correlates of human speech. One of the most important aspects of human auditory perception is the nonlinearity which should be incorporated into the linear speech analysis and synthesis system. Further studies using more sophisticated equipment are desirable to refine these scales, through the analysis of human auditory perception of complex tones or speech. This will lead scientists to develop better speech recognition and synthesis devices.

• The Journal of the Acoustical Society of Korea
• /
• v.2 no.1
• /
• pp.11-19
• /
• 1983

An irregulary formed chamber was designed and constructed to recognize the direct sound radiated from the sound source and the reflected sound from the walls of the chamber. The sound signal used was tone burst in the frequency response characteristics with the signal detection after transient effect. The direct wave, transient phenomena and the primary reflected sound could be asiily distinguished each other by measurements of the arrival time of the time difference. And also noise could be easily distinguished by the same method. The result obtained can be used in industries for automatic measurement of the sound pressure reponse characteristics with respect to frequencies.

• Speech Sciences
• /
• v.7 no.4
• /
• pp.219-234
• /
• 2000

The study of boundary tones in connected speech or dialogues is one of the most underdeveloped areas of Korean prosody. This. paper concerns the boundary tones of intonational phrase-final morphemes which are shown in the speech corpus of dialogues. Results of phonetic analysis show that different kinds of boundary tones are realized, depending on the positions of the intonational phrase-final morphemes in the sentences.. This study has also shown that boundary tone patterning is somewhat related to the sentence structure, and for better speech recognition and speech synthesis, it presents a simple model of boundary tones based on the fundamental frequency contour. The results of this study will contribute to our understanding of the prosodic pattern of Korean connected speech or dialogues.

• The Journal of the Korea Contents Association
• /
• v.15 no.11
• /
• pp.1-9
• /
• 2015

Emotion recognition and regular controls are concentrated interest in computer studies to emotional changes. Thus, the quantified by objective assessment methods are essential for application of color sensibility computing situations. In this paper, it is applied to a digital color image emotion emotional computing calculations numbered recognized as one representation. Emotional computing research approach consists of a color attribute to the image recognition focused sensibility and emotional attributes of color is the color, brightness and saturation separated by. Computes the sensitivity weighted according to the score and the percentage increase or decrease in the sensitivity property tone applied to emotional expression. Sensitivity calculation is free-degree (X), and calculates the tension (Y-axis). And free-level (X-axis) coordinate of emotion, which is located the intersection of the tension (Y-axis) as a sensitivity point. The emotional effect of the Russell coordinates are utilizing the core (Core Affect). Tue numbers represent the size and sensitivity in the emotional relationship between emotional point location and quantified by computing the color sensibility.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.23-28
• /
• 2022

Today, the online market has grown rapidly due to the development of digital platforms and the pandemic situation. Therefore, unlike the existing offline market, the distinctiveness of the online market has prompted users to check online reviews. It has been established that reviews play a significant part in influencing the user's purchase intention through precedents of several studies. However, the current review writing method makes it difficult for other users to understand the writer's emotions by expressing them through elements like tone and words. If the writer also wanted to emphasize something, it was very cumbersome to thicken the parts or change the colors to reflect their emotions. Therefore, in this paper, we propose a technique to check the user's emotions through facial expression recognition using a camera, to automatically set colors for each emotion using research on existing emotions and colors, and give colors based on the user's intention.

• Journal of the Korean Society of Costume
• /
• v.56 no.4 s.103
• /
• pp.160-170
• /
• 2006

The purpose of this study is to analyze the image of color combination in fashion design. For this study 14,121 color samples were collected from 116 fashion brands selected by the market segmentation based on the results of the previous studies. The brands have high market share and brand recognition in each segmental market. The color samples were measured by spectrophotometer and analyzed by the Munsell's H V/C and CIE $L^*a^*b^*$ value. The representative colors of each market were selected concerning the tensity in CIE $L^*a^*b^*$ color space and the distance between the color samples. h4 a result, 2,213 representative colors were chosen. These color samples composed top and bottom color combination samples by the program 'Item Comparator' that calculated the color differences$({\Delta}E^*)$. Top includes the items such as blouse, shirt, and coats, bottom includes the items such as skirt and pants. The color combination samples were divided into two groups. In one group ${\Delta}E^*$ was less than 30, and In the other group ${\Delta}E^*$ was 30 or more. For investigating the image of color combination, 480 rotor combination samples were classified. The image adjectives for the survey from preceding studies and brand dictionaries were 'classic', 'modern', 'feminine', 'casual', and 'romantic', which have highly preferred in women's wear brands. The result of the study is as follows; For 'classic' 'image, YR, and greyish tone were generally preferred. In the color combination of 'casual' image, the samples with PB color and greyish tone were preferred. For 'feminine' image, RP was preferred as a top color, R, RP, P were preferred as a bottom color. For 'casual' image, PB was preferred as a top color, PB, B were preferred as a bottom color. For 'romantic' image, RP was preferred as a top color, R, P were preferred as a bottom color. The bigger the color differences between the color combination samples were, the more remarkable the image of color combination samples was.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.675-681
• /
• 2021

With the recent growth of the AI speaker market, the demand for speech synthesis technology that enables natural conversation with users is increasing. Therefore, there is a need for a multi-speaker speech synthesis system that can generate voices of various tones. In order to synthesize natural speech, it is required to train with a large-capacity. high-quality speech DB. However, it is very difficult in terms of recording time and cost to collect a high-quality, large-capacity speech database uttered by many speakers. Therefore, it is necessary to train the speech synthesis system using the speech DB of a very large number of speakers with a small amount of training data for each speaker, and a technique for naturally expressing the tone and rhyme of multiple speakers is required. In this paper, we propose a technology for constructing a speaker encoder by applying the deep learning-based x-vector technique used in speaker recognition technology, and synthesizing a new speaker's tone with a small amount of data through the speaker encoder. In the multi-speaker speech synthesis system, the module for synthesizing mel-spectrogram from input text is composed of Tacotron2, and the vocoder generating synthesized speech consists of WaveNet with mixture of logistic distributions applied. The x-vector extracted from the trained speaker embedding neural networks is added to Tacotron2 as an input to express the desired speaker's tone.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.157-163
• /
• 2014

User's sensitivity is recognized as a very important parameter for communication between company, government and personnel. Especially in many studies, researchers use voice tone, voice speed, facial expression, moving direction and speed of body, and gestures to recognize the sensitivity. Multiplex modality is more precise than single modality however it has limited recognition rate and overload of data processing according to multi-sensing also an excellent algorithm is needed to deduce the sensing value. That is as each modality has different concept and property, errors might be happened to convert the human sensibility to standard values. To deal with this matter, the sensibility expression modality is needed to be extracted using technologies like analyzing of relational network, understanding of context and digital filter from multiplex modality. In specific situation to recognize the sensibility if the priority modality and other surrounding modalities are processed to implicit values, a robust system can be composed in comparison to the consuming of computer resource. As a result of this paper, it is proposed how to assign the weight of multiplex modality using implicit data.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.12
• /
• pp.1679-1690
• /
• 2002

This paper, describe about a generation of a syllable restoration regulation for a post processing of a speech recognition and a decrease of a restoration candidate. It created a syllable restoration regulation to create a restoration candidate pronounced with phonetic value recognized through a post processing of the formula system that was a tone to recognize syllable unit phonetic value for a performance enhancement of a dialogue serial speech recognition. Also, I presented a plan to remove a regulation to create unused notation from a real life in a restoration regulation with a plan to reduce number candidate of a restoration meeting. A design implemented a restoration candidate set generator in order a syllable restoration regulation display that it created a proper restoration candidate set. The proper notation meeting that as a result of having proved about a standard pronunciation example and a word extracted from a pronunciation dictionary at random, the notation that an utterance was former was included in proved with what a generation became.

• Korean Journal of Human Ecology
• /
• v.18 no.5
• /
• pp.1077-1086
• /
• 2009

In this study, the effect of clothing color preferences of adolescents on their self expression desires and fashion interest were investigated. These investigations were intended to understand some psychological aspects of adolescents and to make a contribution to guiding them in forming self identities and expressing themselves confidently through clothing. This research was based on 452 copies of questionnaires distributed to middle and high school students living in Seoul and other metropolitan areas from the middle of March to the beginning of April, 2008. The results were as follows. First, there was a significant difference in clothing color preference and clothing color tone preference between male students and female students. Second, the factor analysis which has been performed by taking assimilation, individuality, recognition, and image management as composing dimensions of self expression desire shows significant differences between these dimensions. Third, the difference in the self expression desires according to clothing color preference showed that the group preferring cool colors and the group preferring warm colors possessed the same highest self expression desires. And, it was revealed that the clothing color preference was a significant variable influencing fashion interest. Fourth, the effect of self expression desire on the fashion interest degree showed that recognition was the most significant factor and image management was the next.