• Title/Summary/Keyword: Sound recognition

Search Result 311, Processing Time 0.029 seconds

A Korean menu-ordering sentence text-to-speech system using conformer-based FastSpeech2 (콘포머 기반 FastSpeech2를 이용한 한국어 음식 주문 문장 음성합성기)

  • Choi, Yerin;Jang, JaeHoo;Koo, Myoung-Wan
    • The Journal of the Acoustical Society of Korea
    • /
    • v.41 no.3
    • /
    • pp.359-366
    • /
    • 2022
  • In this paper, we present the Korean menu-ordering Sentence Text-to-Speech (TTS) system using conformer-based FastSpeech2. Conformer is the convolution-augmented transformer, which was originally proposed in Speech Recognition. Combining two different structures, the Conformer extracts better local and global features. It comprises two half Feed Forward module at the front and the end, sandwiching the Multi-Head Self-Attention module and Convolution module. We introduce the Conformer in Korean TTS, as we know it works well in Korean Speech Recognition. For comparison between transformer-based TTS model and Conformer-based one, we train FastSpeech2 and Conformer-based FastSpeech2. We collected a phoneme-balanced data set and used this for training our models. This corpus comprises not only general conversation, but also menu-ordering conversation consisting mainly of loanwords. This data set is the solution to the current Korean TTS model's degradation in loanwords. As a result of generating a synthesized sound using ParallelWave Gan, the Conformer-based FastSpeech2 achieved superior performance of MOS 4.04. We confirm that the model performance improved when the same structure was changed from transformer to Conformer in the Korean TTS.

Consideration for cognitive effects in smart environments for effective UXD(User eXperience Design) (스마트환경의 효과적인 UXD를 위한 인지작용 고찰)

  • Lee, Chang Wook;Chung, Jean-Hun
    • Journal of Digital Convergence
    • /
    • v.11 no.2
    • /
    • pp.397-405
    • /
    • 2013
  • The development of the technology of the 21st century, wireless Internet technology development in smart environments, was rapidly settled. In such an environment, the user is faced with many smart devices and smart content. This study is the analysis of the smart environment and smart devices, and user-to-user cognitive out about the effects reported. Cognitive effects observed behavior, technology, and user-centered system design, and plays a very important role to play in educating the users. And theoretical consideration about the UX (User eXperience) and UXD (User eXperience Design), by case analysis on the technical aspects of 'effective' visual aspect of interoperation aspects (interaction), and the cognitive effects of UXD (User eXperience Design) examined. As a result, on the visual aspects of the user experience based on the design that can be used to know, and be sound or through interaction with the user of the machine-to-machine interaction (and interaction) that must be provided, such as location-based or speech recognition technology will help you through the convenience of the user. Through this research, the smart environment and helping act of understanding, effective UXD (User eXperience Design) to take advantage of to help.

Smart Affect Jewelry based on Multi-modal (멀티 모달 기반의 스마트 감성 주얼리)

  • Kang, Yun-Jeong
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.20 no.7
    • /
    • pp.1317-1324
    • /
    • 2016
  • Utilizing the Arduino platform to express the emotions that reflect the colors expressed the jewelry. Emotional color expression utilizes Plutchik's Wheel of Emotions model was applied to the similarity of emotions and colors. It receives the recognized value from the temperature, lighting, sound, pulse sensor and gyro sensor of a smart jewelery that can be easily accessible from your smartphone processes that recognize and process the emotion applied the rules of inference based on ontology. The emotional feelings color depending on the color looking for the emotion seen in context and applied to the smart LED jewelry. The emotion and the color combination of contextual information extracted from the recognition sensors are reflected in the built-in smart LED Jewelry depending on the emotions of the wearer. Take a light plus the emotion in a smart jewelery can represent the emotions of the situation, the doctor will be able to be a tool of representation.

User Interaction Library for Natural Science Education Digital App-Book on Android Platform (안드로이드 기반 자연과학 교육용 디지털 앱북 개발을 위한 사용자 상호작용 라이브러리)

  • Lee, Kang-Woon;Beak, A-Ram;Choi, Haechul
    • Journal of Broadcast Engineering
    • /
    • v.20 no.1
    • /
    • pp.110-121
    • /
    • 2015
  • The digital app-book is an advanced form of the electronic book (e-book), which attracts a lot of interests by the help of video, sound, sensors and a variety of interactions. As mobile devices have evolved, the demand of digital app-books is also rising substantially. However, the distribution of digital app-book contents is hard to meet the demand because the digital app-book requires a lot of programming cost for the interaction. To resolve this problem, Was verified and implementation as a library function of the interaction between device and user. The proposed library consists of three parts (user action recognition, device action, and content action) and provides various user-device interaction functions by combining methods of each part, which can support source code reusability, easy understanding and availability, and wide expandibility. The library was used in the development of natural science education app-book contents. As a result, it could reduce a lot of code lines and facilitate more rapid app-book development.

A Study on Environment and Perception of CAD by Undergraduate Students in the Dept. of Architecture - Case study on Undergraduate Students - (대학(大學) 건축학과(建築學科) 재학생(在學生)의 CAD 환경(環境) 및 인식(認識)에 관한 연구(硏究) - 사례대학의 재학생을 대상으로 -)

  • Yoo, Chang-Geun;Park, Sung-Ha
    • Journal of The Korean Digital Architecture Interior Association
    • /
    • v.1 no.1
    • /
    • pp.24-30
    • /
    • 2001
  • This study conducts a questionnaire with undergraduate students in the Dept. of Architecture who will lead the architectural field in future, examines environment and perception of CAD in their home and universities and aims at supplying the data required for setting CAD educational index and building its use environment, and it could obtain the following results. Individual CAD environment of undergraduate students in the Dept. of Architecture reach a considerable level in hardware part, but they don't have the same level in software part as the hardware and use illegal copy programs. It is shown that they spend their time in using CAD for five to eight hours a week and its main purposes are to perform a project related to architectural design or make report requiring drawing. Major places using CAD are CAD room in university or public PC room equipped with CAD compared to their own houses and most of them have a negative recognition of the convenience of its use. Their satisfaction with CAD use is considerably high and when they submitted their assignments of architectural design project by means of CAD, they had a positive evaluation from their professors and they have such hopes that 'Korean Support Strengthening', 'lowering price through version supply for students' and 'diversification of design symbol' in CAD S/W, and especially, most of respondents have an intention to purchase the original goods when version only for students will be marketed in future. Accordingly, for a qualitative improvement of CAD environment for undergraduate students in the Dept. of Architecture, universities must be equipped with the various types of CAD S/W and Applications and students' opportunity to access them should be increased. In addition, a method which can enhance using convenience of CAD room and PC room is required and CAD related S/W developers must market the version for students which consider the reality of undergraduates in Korea properly with an appropriate price level in order to settle a sound S/W culture.

  • PDF

Content-based Music Information Retrieval using Pitch Histogram (Pitch 히스토그램을 이용한 내용기반 음악 정보 검색)

  • 박만수;박철의;김회린;강경옥
    • Journal of Broadcast Engineering
    • /
    • v.9 no.1
    • /
    • pp.2-7
    • /
    • 2004
  • In this paper, we proposed the content-based music information retrieval technique using some MPEG-7 low-level descriptors. Especially, pitch information and timbral features can be applied in music genre classification, music retrieval, or QBH(Query By Humming) because these can be modeling the stochasticpattern or timbral information of music signal. In this work, we restricted the music domain as O.S.T of movie or soap opera to apply broadcasting system. That is, the user can retrievalthe information of the unknown music using only an audio clip with a few seconds extracted from video content when background music sound greeted user's ear. We proposed the audio feature set organized by MPEG-7 descriptors and distance function by vector distance or ratio computation. Thus, we observed that the feature set organized by pitch information is superior to timbral spectral feature set and IFCR(Intra-Feature Component Ratio) is better than ED(Euclidean Distance) as a vector distance function. To evaluate music recognition, k-NN is used as a classifier

The Research about Image on Korean Medicine (한의학 관련 이미지 연구)

  • Kim, Jae-Ik;Myeong, Ye-Seul;Ahn, Soo-Yeon;Lee, Yeong-Ji;Cho, Chung-Sik
    • The Journal of Internal Korean Medicine
    • /
    • v.35 no.3
    • /
    • pp.354-365
    • /
    • 2014
  • Objectives: Recently, the utility rate of Korean-Medical service has been a 6 percent of the domestic market share in medical service, so there is a lot of effort to increase utility rate of Korean medical service. However, in spite of the importance of image to promotion, there are still few studies about image of Korean medicine. Thus, the purpose of this study was to suggest ways to increase utility rate of Korean medical service by surveying and analysing recognition of image of Korean Medicine. Methods: People aged between 20s and 40s were targets of investigation. We divided respondents into three groups depending on relation approximation with Korean medicine (weak-related group, normal-related group, strong-related group). The questionnaire consisted of questions about images of Korean medicine, conducted through online and personal interviews. Results: In total, 282 members responded to the survey and the results of the analysis were as follows. The more a person was related to Korean medicine, the greater the tendency to experience Korean medical service. The most associated taste about Korean medical institutions was Bitterness, smell was smell of Korean medicine, color was yellow, feeling was warm, sound (instrument) was drum, and treatment pattern was Acupuncture, respectively. The most associated image of acupuncture was painful, and the most associated age of Korean medical doctors was 40s. The most associated general term of Korean medicine was physical constitution, and most associated pathological term was extravasated blood. Conclusions: This study can be very useful for future image marketing of Korean medicine because there have been no other studies about image on Korean medicine before now. But this study has also some limits like area, respondent selection, etc., so a more detailed and comprehensive survey is needed.

A Development of Infant Education Content for Animal Study (동물모형 학습을 위한 유아교육 콘텐츠 개발)

  • Lee, Kwang-Hyoung;Kim, Jung-Jae
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.11 no.9
    • /
    • pp.3510-3516
    • /
    • 2010
  • In this paper to make young children to learn habits of the animals, crying, features, and English and Korean language, The system was developed to target the zoo various animals exist. If young child places a doll on the front of interesting animal, then young child can learn to look through the display connected to the model. The zoo is reducing the current appearance of the zoo, sensors that can recognize animals are attached to each cage. Attached to each sensor has a unique ID, If this approach recognizes a doll baby and will transmit a unique ID to the handler. Transmitted ID search the matched value sent from the database to retrieve the content and then the content is to be output through the output device. Also if the doll near the animal's room, young children find out animal sound and basic learning by multimedia effects. At the same time Korean, English, Mathematics are learned.

Developments and Trends in Fisheries Processing: Value-Added Product Development and Total Resource Utilization

  • Meyers Samuel P.
    • Korean Journal of Fisheries and Aquatic Sciences
    • /
    • v.27 no.6
    • /
    • pp.839-846
    • /
    • 1994
  • Changing concepts in fishery science increasingly are recognizing depletion of traditional stocks, utilization of alternate(non-traditional) species, demand for high quality products, and a total resource utilization approach. Innovative practices are occurring in fisheries processing wherein solid and liquid discharges are no longer treated as 'waste,' but rather as valuable feedstocks for recovery of a variety of value-added ('value enhanced') by-products. Among these are protein hydrolysates, soluble proteins and amino acids, proteolytic enzymes, flavor and flavor extracts, pigments, and biopolymers such as chitosan. Properties and applications of this deacetylated derivative of chitin are noted. Crustacean processing by-products are discussed in terms of their serving as materials for generation of natural flavors and flavor extracts, and products such as fish sauces using contemporary enzymatic techniques. Various food and feed applications of fisheries processing by-products are illustrated with increased usage seen in formulated diets for an expanding aquaculture market. Examples are given of aquaculture becoming increasingly significant in global fisheries resource projections. Critical issues in the international seafood industry Include those of seafood quality, processing quality assurance (HACCP), and recognition of the nutritional and health-related properties of fisheries products. A variety of current seafood processing research is discussed, including that of alternate fish species for surimi manufacture and formulation of value-added seafood products from crawfish and blue crab processing operations. Increasing emphasis is being placed on international aspects of global fisheries and the role of aquaculture in such considerations. Coupled with the need for the aquatic food industry to develop innovative seafood products for the 21st century is that of total resource utilization. Contemporary approaches in seafood processing recognize the need to discard the traditional concept of processing 'waste' and adapt a more realistic, and economically sound, approach of usable by-products for food and feed application. For example, in a period of declining natural fishery resources it is no longer feasible to discard fish frames following fillet removal when a significant amount of residual valuable flesh is present that can be readily recovered and properly utilized in a variety of mince-based formulated seafood products.

  • PDF

A Study on the Development of Computer Assisted Instruction for the Middle School Mathematics Education - Focused on the graph of quadratic function - (중학교 수학과 CAI 프로그램 개발 연구 -이차함수의 그래프를 중심으로-)

  • 장세민
    • Journal of the Korean School Mathematics Society
    • /
    • v.1 no.1
    • /
    • pp.151-163
    • /
    • 1998
  • In mathematics education, teaching-learning activity can be divided largely into the understanding the mathematical concepts, derivation of principles and laws, acquirement of the mathematical abilities. We utilize various media, teaching tools, audio-visual materials, manufacturing materials for understanding mathematical concepts. But sometimes we cannot define or explain correctly the concepts as well as the derivation of principles and laws by these materials. In order to solve the problem we can use the computer. In this paper, character and movement state of various quadratic function graph types can be used. Using the computers is more visible than other educational instruments like blackboards, O.H.Ps., etc. Then, students understand the mathematical concepts and the correct quadratic function graph correctly. Consquently more effective teaching-learning activity can be done. Usage of computers is the best method for improving the mathematical abilities because computers have functions of the immediate reaction, operation, reference and deduction. One of the important characters of mathematics is accuracy, so we use computers for improving mathematical abilities. This paper is about the program focused on the part of "the quadratic function graph", which exists in mathematical curriculum the middle school. When this program is used for students, it is expected the following educational effect. 1, Students will have positive thought by arousing interests of learning because this program is composed of pictures, animations with effectiveness of sound. 2. This program will cause students to form the mathematical concepts correctly. 3. By visualizing the process of drawing the quadratic function graph, students understand the quadratic function graph structually. 4. Through the feedback, the recognition ability of the trigonometric function can be improved. 5. It is possible to change the teacher-centered instruction into the student-centered instruction. For the purpose of increasing the efficiencies and qualities of mathmatics education, we have to seek the various learning-teaching methods. But considering that no computer can replace the teacher′s role, tearchers have to use the CIA program carefully.

  • PDF