Zobrazeno 1 - 10 of 20 pro vyhledávání: '"Kim, Jaebok"'
1
Report
Comparison of Speech Representations for the MOS Prediction System
Autor: Kunikoshi, Aki, Kim, Jaebok, Jun, Wonsuk, Sjölander, Kåre
Automatic methods to predict Mean Opinion Score (MOS) of listeners have been researched to assure the quality of Text-to-Speech systems. Many previous studies focus on architectural advances (e.g. MBNet, LDNet, etc.) to capture relations between spec
Externí odkaz: http://arxiv.org/abs/2206.13817
Zobrazit plný text záznamu
2
Report
Data-augmented cross-lingual synthesis in a teacher-student framework
Autor: de Korte, Marcel, Kim, Jaebok, Kunikoshi, Aki, Adigwe, Adaeze, Klabbers, Esther
Cross-lingual synthesis can be defined as the task of letting a speaker generate fluent synthetic speech in another language. This is a challenging task, and resulting speech can suffer from reduced naturalness, accented speech, and/or loss of essent
Externí odkaz: http://arxiv.org/abs/2204.00061
Zobrazit plný text záznamu
3
Report
Efficient neural speech synthesis for low-resource languages through multilingual modeling
Autor: de Korte, Marcel, Kim, Jaebok, Klabbers, Esther
Recent advances in neural TTS have led to models that can produce high-quality synthetic speech. However, these models typically require large amounts of training data, which can make it costly to produce a new voice with the desired quality. Althoug
Externí odkaz: http://arxiv.org/abs/2008.09659
Zobrazit plný text záznamu
4
Report
Planning Based System for Child-Robot Interaction in Dynamic Play Environments
Autor: Charisi, Vicky, Ridder, Bram, Kim, Jaebok, Evers, Vanessa
This paper describes the initial steps towards the design of a robotic system that intends to perform actions autonomously in a naturalistic play environment. At the same time it aims for social human-robot interaction~(HRI), focusing on children. We
Externí odkaz: http://arxiv.org/abs/1708.06445
Zobrazit plný text záznamu
5
Report
Learning spectro-temporal features with 3D CNNs for speech emotion recognition
Autor: Kim, Jaebok, Truong, Khiet P., Englebienne, Gwenn, Evers, Vanessa
In this paper, we propose to use deep 3-dimensional convolutional networks (3D CNNs) in order to address the challenge of modelling spectro-temporal dynamics for speech emotion recognition (SER). Compared to a hybrid of Convolutional Neural Network a
Externí odkaz: http://arxiv.org/abs/1708.05071
Zobrazit plný text záznamu
6
Report
Towards Speech Emotion Recognition 'in the wild' using Aggregated Corpora and Deep Multi-Task Learning
Autor: Kim, Jaebok, Englebienne, Gwenn, Truong, Khiet P., Evers, Vanessa
One of the challenges in Speech Emotion Recognition (SER) "in the wild" is the large mismatch between training and test data (e.g. speakers and tasks). In order to improve the generalisation capabilities of the emotion models, we propose to use Multi
Externí odkaz: http://arxiv.org/abs/1708.03920
Zobrazit plný text záznamu
7
Akademický článek
Automatic temporal ranking of children’s engagement levels using multi-modal cues
Autor: Kim, Jaebok, Truong, Khiet P., Evers, Vanessa
Publikováno v: In Computer Speech & Language July 2018 50:16-39
Zobrazit plný text záznamu
8
End-to-end listening agent for audiovisual emotional and naturalistic interactions
Autor: Haddad, Kevin EI, Rizk, Yara, Heron, Louise, Hajj, Nadine, Zhao, Yong, Kim, Jaebok, Trong, Trung Ngo, Lee, Minha, Doumit, Marwan, Lin, Payton, Kim, Yelin, Çakmak, Hüseyin
Publikováno v: Journal of Science and Technology of the Arts; Vol 10 No 2 (2018): eNTERFACE 2017; 49-61
Journal of Science and Technology of the Arts; v. 10 n. 2 (2018): eNTERFACE 2017; 49-61
Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Journal of Science and Technology of the Arts; Vol 10 No 2 (2018): Volume 10-Number 2, 2018 (Special Issue); 2-49-61
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Agência para a Sociedade do Conhecimento (UMIC)-FCT-Sociedade da Informação
Journal of Science and Technology of the Arts, 10(2), 49-61. Catholic University of Portugal
Journal of Science and Technology of the Arts, 10(2), 49-61. Portuguese Catholic University
Journal of Science and Technology of the Arts, Vol 10, Iss 2 (2018)
In this work, we established the foundations of a framework with the goal to build an end-to-end naturalistic expressive listening agent. The project was split into modules for recognition of the user’s paralinguistic and nonverbal expressions, pre
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::52ae531d01b3be08c241b4b804c1a5bd
https://research.tue.nl/en/publications/6781b40f-1098-43d2-872d-940605af9fe7
Zobrazit plný text záznamu
10
Multimodal Detection of Engagement in Groups of Children Using Rank Learning
Autor: Kim, Jaebok, Truong, Khiet Phuong, Charisi, Vasiliki, Zaga, Cristina, Evers, Vanessa, Chetouani, Mohamed, Cohn, Jeffrey, Salah, Albert Ali
Publikováno v: Human Behavior Understanding: 7th International Workshop, HBU 2016, Amsterdam, The Netherlands, October 16, 2016, Proceedings, 35-48
STARTPAGE=35;ENDPAGE=48;TITLE=Human Behavior Understanding
Human Behavior Understanding ISBN: 9783319468426
HBU
Human Behavior Understanding
Human Behavior Understanding, pp.35-48, 2016, ⟨10.1007/978-3-319-46843-3_3⟩
In collaborative play, children exhibit different levels of engagement. Some children are engaged with other children while some play alone. In this study, we investigated multimodal detection of individual levels of engagement using a ranking method
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8512900804d8b1940208107b8ae9c623
https://research.utwente.nl/en/publications/0e2b223e-9d95-4e3e-b691-cc6f9d6dd219
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje