• Title/Summary/Keyword: representation.

Search Result 6,172, Processing Time 0.029 seconds

One-shot multi-speaker text-to-speech using RawNet3 speaker representation (RawNet3를 통해 추출한 화자 특성 기반 원샷 다화자 음성합성 시스템)

  • Sohee Han;Jisub Um;Hoirin Kim
    • Phonetics and Speech Sciences
    • /
    • v.16 no.1
    • /
    • pp.67-76
    • /
    • 2024
  • Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.

Psychological Symbolism of the Shamanic Song of Princess Bari : From the Perspective of Analytical Psychology (무가 바리공주의 심리학적 상징성 : 분석심리학적 입장에서)

  • Young Hee Kim
    • Sim-seong Yeon-gu
    • /
    • v.36 no.1
    • /
    • pp.1-54
    • /
    • 2021
  • Princess Bari, the seventh daughter of the King and Queen, is abandoned at birth. She one day embarks on a solitary journey into the underworld to seek the antidote she needs to save her ailing father. The shamanic myth then depicts terrible ordeals, after which the Princess manages to obtain the elixir of life to bring her parents back to life, leading to her deification as the Queen of all shamans. The life of Princess Bari as the ancestor of shamans incorporates the necessary rite of passage to become a shaman, persevering through all manner of trials and tribulations until death and then being reborn. Princess Bari's story of deification as the goddess of shamans constitutes the archetype or the primitive image of the collective unconscious, the mytheme. From the perspective of analytical psychology, Princess Bari, who became the Queen of shamans after undergoing a process of pain, death, and then rebirth demonstrates a facet of the individuation process, evident in heroic mythology. Princess Bari not only cured her parents of disease but also brought them back to life. What enabled her to obtain the elixir to resurrect her parents was her love and compassion for them based on self-sacrifice, enduring all the trivial and repetitive undertakings of everyday life. She viewed the world and behaved from the perspective of a broader Self. Making herself a powerful healer through the ordeals in the underworld, Princess Bari is the psychopomp as well as the healer archetype. The sacred power of healing that goes beyond the Princess' sufferings represents the Self Archetype inherent in the mentality of the Koreans, in other words, a symbolic power that indicates the divine representation of a healer.

A Study on Records as an Act of Artistic Creation: Focusing on Archival Art (예술창작 행위로서의 기록에 대한 고찰 아카이브 아트를 중심으로)

  • Lee, Hosin
    • The Korean Journal of Archival Studies
    • /
    • no.80
    • /
    • pp.197-232
    • /
    • 2024
  • This study aims to understand archival art, which is spreading in the art world, and to look at records in a new way. Archival art refers to the act of creating and exhibiting art using records as a medium of expression. Archival art is attracting attention as a method of exhibition and creation of works, forming a trend in contemporary art. Archival art was born amid changes in art creation methods resulting from the rise of conceptual art, the development of media including photography and advancements in digital technology, and the influence of Foucault and Derrida's discourse on archives. The encounter between archives and art, which originated from photographic aesthetics in the 1920s, led to archival turn in contemporary art in the 1990s, thanks to the spread of conceptual art, digital technology, and postmodernism. Archival art not only subverts traditional art creation methods, but also includes criticism and deconstruction of social systems, including modern archives. Archival art rearranges and reorganizes records according to the artist's intention, and even accepts fiction rather than fact. The essence of records in archival art is not the reproduction of the past, but the expression of present needs. The way records are utilized in archival art shakes up the concept of records in archival science, calling for a new look at records as objects with not only legal and administrative value but also aesthetic value.

Current Status, Challenges, and Suggestions for Utilizing Daesoon Jinrihoe's Video Content: Focusing on the Film, The Road of Peace and Harmony, and the Videos of the Museum of Daesoon Jinrihoe (신종교의 영상 콘텐츠 활용 현황과 과제, 그리고 제언 - 영화 <화평의 길>과 대순진리회박물관의 영상물을 중심으로-)

  • Park Jong-soo
    • Journal of the Daesoon Academy of Sciences
    • /
    • v.48
    • /
    • pp.239-268
    • /
    • 2024
  • Video content is often used as a means of education due to the characteristics of the medium: representation, information delivery, immersion, and experience. In particular, religious films are being used more often in public schools and religious communities to promote understanding and inspiration. The purpose of this study is to examine how Daesoon Jinrihoe utilizes video content via the film, The Road to Peace and Harmony, and the videos that were made for the Museum of Daesoon Jinrihoe Museum. The study will also make suggestions regarding the future use of such contents. In Section 2 of this study, the status of the video contents as currently used by Daesoon Jinrihoe will be examined and analyzed in terms of how the film, The Road to Peace and Harmony, and the videos produced for the Museum of Daesoon Jinrihoe are being utilized. In Section 3, the limitations of Daesoon Jinrihoe's video contents will be considered in that these materials in terms of how these videos are only used within the religious order. There is the potential that such materials could be used in broader society. Lastly, in Section 4, it is proposed that video materials produced by Daesoon Jinrihoe could be used within multicultural religious education in a public setting beyond mere in-group religious education. Through this, it is hoped that Daesoon Jinrihoe will be able to expand as a world religion in a more timely manner than what would otherwise be achieved.

Improvement of Face Recognition Algorithm for Residential Area Surveillance System Based on Graph Convolution Network (그래프 컨벌루션 네트워크 기반 주거지역 감시시스템의 얼굴인식 알고리즘 개선)

  • Tan Heyi;Byung-Won Min
    • Journal of Internet of Things and Convergence
    • /
    • v.10 no.2
    • /
    • pp.1-15
    • /
    • 2024
  • The construction of smart communities is a new method and important measure to ensure the security of residential areas. In order to solve the problem of low accuracy in face recognition caused by distorting facial features due to monitoring camera angles and other external factors, this paper proposes the following optimization strategies in designing a face recognition network: firstly, a global graph convolution module is designed to encode facial features as graph nodes, and a multi-scale feature enhancement residual module is designed to extract facial keypoint features in conjunction with the global graph convolution module. Secondly, after obtaining facial keypoints, they are constructed as a directed graph structure, and graph attention mechanisms are used to enhance the representation power of graph features. Finally, tensor computations are performed on the graph features of two faces, and the aggregated features are extracted and discriminated by a fully connected layer to determine whether the individuals' identities are the same. Through various experimental tests, the network designed in this paper achieves an AUC index of 85.65% for facial keypoint localization on the 300W public dataset and 88.92% on a self-built dataset. In terms of face recognition accuracy, the proposed network achieves an accuracy of 83.41% on the IBUG public dataset and 96.74% on a self-built dataset. Experimental results demonstrate that the network designed in this paper exhibits high detection and recognition accuracy for faces in surveillance videos.

Usability Evaluation Criteria Development and Application for Map-Based Data Visualization (지도 기반 데이터 시각화 플랫폼 사용성 평가 기준 개발 및 적용 연구)

  • Sungha Moon;Hyunsoo Yoon;Seungwon Yang;Sanghee Oh
    • Journal of the Korean Society for Library and Information Science
    • /
    • v.58 no.2
    • /
    • pp.225-249
    • /
    • 2024
  • The purpose of this study is to develop an evaluation tool for map-based data visualization platforms and to conduct heuristic usability evaluations on existing platforms representing inter-regional information. We compared and analyzed the usability evaluation criteria of map-based platforms from the previous studies along with Nielsen's (1994) 10 usability evaluation principles. We proposed nine evaluation criteria, including (1) visibility, (2) representation of the real world, (3) consistency and standards, (4) user control and friendliness, (5) flexibility, (6) design, (7) compatibility, (8) error prevention and handling, and (9) help provision and documentation. Additionally, to confirm the effectiveness of the proposed criteria, four experts was invited to evaluate five domestic and international map-based data visualization platforms. As a result, the experts were able to rank the usability of the five platforms using the proposed map-based data visualization usability evaluation criteria, which included quantified scores and subjective opinions. The results of this study are expected to serve as foundational material for the future development and evaluation of map-based visualization platforms.

The Historic Value of Photographic Records in the News and Culture Magazine 'Sasanggye' (시사교양잡지 『사상계』의 사진기록물과 기록학적 가치)

  • Jung, Eun Ah;Park, Ju Seok
    • The Korean Journal of Archival Studies
    • /
    • no.79
    • /
    • pp.471-513
    • /
    • 2024
  • The monthly news and culture magazine, 'Sasanggye,' established by Jang Jun-ha from 1953 to 1970, served as a platform for government criticism and intellectual representation. The magazine created photographic-essays covering a variety of topics and utilized images as a visually impactful tool with news value. This paper aims to critically examine the photographic-essays within 'Sasanggye' as archival records, shedding light on their intrinsic value. Before delving into this assessment, the paper thoroughly explores the developmental process and characteristics of these photographic-essays. And based on the content divisions within the main text, the paper categorized the themes captured in the photographic essays into politics, economics, society, culture, and miscellaneous topics. It then introduced representative photographicessays. From an archival perspective, looking at photographs involves elucidating that photographs carry meanings beyond mere data. The photographic essays in 'Sasanggye' serve as photographic records providing evidence of 1960s Korean society and encapsulating crucial visual information. Furthermore, the photographic essays in 'Sasanggye' hold a historical significance in the aspect of Korean magazine documentary photography. The photo-essays in 'Sasanggye' carry worth in the history of photography and encompass evidential and informational values as photographic records.

Investigating Paid Virtual Live Stream Concert Experience from the Perspective of Social Representations Theory (유료 온라인 라이브콘서트 소비경험에 대한 연구: 사회표상이론을 중심으로)

  • Hyunjin Park;Yoonhyuk Jung
    • Information Systems Review
    • /
    • v.25 no.2
    • /
    • pp.77-101
    • /
    • 2023
  • Due to COVID-19, paid virtual live-stream concerts have emerged as an alternative format and a new revenue model for in-person live concerts. Despite the increasing scholarly and practical interest in how participants experience paid virtual live-stream concerts, few studies examined participants' consumption and participation experiences. Thus, this study aims to provide insights into consumers' virtual live-stream concert experience by employing social representations theory (SRT). We explore the features of paid virtual live-stream concerts based on the C-P-N-D (Content-Platform-Network-Device) framework and the consumers' cognitive and affective perception. To this end, an SRT-based core-periphery analysis was conducted based on 239 responses to the open-ended survey questions. The results show that network-and device-level features of virtual live concerts and participants' overall perception are presented as core elements of paid virtual live-stream concerts, whereas content- and platform-level features are peripheral elements. This finding provides an in-depth understanding of the emergence of paid virtual live-stream concerts as an alternative concert format, thereby providing an invaluable understanding of a virtual live concert experience and theoretical and practical insights.

Effect of the initial imperfection on the response of the stainless steel shell structures

  • Ali Ihsan Celik;Ozer Zeybek;Yasin Onuralp Ozkilic
    • Steel and Composite Structures
    • /
    • v.50 no.6
    • /
    • pp.705-720
    • /
    • 2024
  • Analyzing the collapse behavior of thin-walled steel structures holds significant importance in ensuring their safety and longevity. Geometric imperfections present on the surface of metal materials can diminish both the durability and mechanical integrity of steel shells. These imperfections, encompassing local geometric irregularities and deformations such as holes, cavities, notches, and cracks localized in specific regions of the shell surface, play a pivotal role in the assessment. They can induce stress concentration within the structure, thereby influencing its susceptibility to buckling. The intricate relationship between the buckling behavior of these structures and such imperfections is multifaceted, contingent upon a variety of factors. The buckling analysis of thin-walled steel shell structures, similar to other steel structures, commonly involves the determination of crucial material properties, including elastic modulus, shear modulus, tensile strength, and fracture toughness. An established method involves the emulation of distributed geometric imperfections, utilizing real test specimen data as a basis. This approach allows for the accurate representation and assessment of the diversity and distribution of imperfections encountered in real-world scenarios. Utilizing defect data obtained from actual test samples enhances the model's realism and applicability. The sizes and configurations of these defects are employed as inputs in the modeling process, aiding in the prediction of structural behavior. It's worth noting that there is a dearth of experimental studies addressing the influence of geometric defects on the buckling behavior of cylindrical steel shells. In this particular study, samples featuring geometric imperfections were subjected to experimental buckling tests. These same samples were also modeled using Finite Element Analysis (FEM), with results corroborating the experimental findings. Furthermore, the initial geometrical imperfections were measured using digital image correlation (DIC) techniques. In this way, the response of the test specimens can be estimated accurately by applying the initial imperfections to FE models. After validation of the test results with FEA, a numerical parametric study was conducted to develop more generalized design recommendations for the stainless-steel shell structures with the initial geometric imperfection. While the load-carrying capacity of samples with perfect surfaces was up to 140 kN, the load-carrying capacity of samples with 4 mm defects was around 130 kN. Likewise, while the load carrying capacity of samples with 10 mm defects was around 125 kN, the load carrying capacity of samples with 14 mm defects was measured around 120 kN.

Analysis of the Manners of Using Scientific Models in Secondary Earth Science Classrooms: With a Focus on Lessons in the Domains of Atmospheric and Oceanic Earth Sciences (중등학교 지구과학 수업에서 과학적 모델의 활용 양상 분석: 대기 및 해양 지구과학 관련 수업을 중심으로)

  • Oh, Phil-Seok
    • Journal of The Korean Association For Science Education
    • /
    • v.27 no.7
    • /
    • pp.645-662
    • /
    • 2007
  • The purpose of this study was to explore the manners in which models are used in secondary science classrooms. A total of thirteen video-recordings of science lessons dealing with the domains of atmospheric and oceanic earth sciences and their verbatim transcripts were analysed both quantitatively and qualitatively. Interviews with three inservice science teachers were also conducted. Six interrelated assertions were generated as the result of the study: 1) The most frequently used models in secondary earth science classrooms include two-dimensional pictorial, symbolic, iconic, and diagrammatic ones; 2) Science teachers employ models as a mode of representation to make the subject matter available to students; 3) In earth science classrooms, teachers use typical forms of models in intensive manners; 4) Students themselves deal with models on a few occasions, but they just follow similar procedures with the same models; 5) Teachers talk rarely about the nature of scientific models and provide few opportunities for students to think about it; and, 6) Teachers in practice think that the value of using models should be appraised in consideration of the pedagogical intentions of the teacher. Implications for science education and science education research were discussed.