Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Gustav Eje Henter"'
Publikováno v:
Applied Sciences, Vol 14, Iss 4, p 1460 (2024)
This paper compares three methods for evaluating computer-generated motion behaviour for animated characters: two commonly used direct rating methods and a newly designed questionnaire. The questionnaire is specifically designed to measure the human-
Externí odkaz:
https://doaj.org/article/ed3d061102ef434cb2f9492db9f5f8ca
Autor:
Patrik Jonell, Birger Moëll, Krister Håkansson, Gustav Eje Henter, Taras Kucherenko, Olga Mikheeva, Göran Hagman, Jasper Holleman, Miia Kivipelto, Hedvig Kjellström, Joakim Gustafson, Jonas Beskow
Publikováno v:
Frontiers in Computer Science, Vol 3 (2021)
Non-invasive automatic screening for Alzheimer’s disease has the potential to improve diagnostic accuracy while lowering healthcare costs. Previous research has shown that patterns in speech, language, gaze, and drawing can help detect early signs
Externí odkaz:
https://doaj.org/article/0833e68562ee4a96a451e97c15df2cdc
Autor:
Pieter Wolfert, Taras Kucherenko, Carla Viegas, Zerrin Yumak, Youngwoo Yoon, Gustav Eje Henter
Publikováno v:
INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f5f2985ce5ec0420e814353c4d4f60a
https://doi.org/10.1145/3536221.3564027
https://doi.org/10.1145/3536221.3564027
Autor:
Youngwoo Yoon, Pieter Wolfert, Taras Kucherenko, Carla Viegas, Teodor Nikolov, Mihail Tsakov, Gustav Eje Henter
Publikováno v:
INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION.
This paper reports on the second GENEA Challenge to benchmark data-driven automatic co-speech gesture generation. Participating teams used the same speech and motion dataset to build gesture-generation systems. Motion generated by all these systems w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2b9fefebd6c856192d9308bfee061fe5
https://doi.org/10.1145/3536221.3558058
https://doi.org/10.1145/3536221.3558058
Autor:
Cassia Valentini-Botinhao, Manuel Sam Ribeiro, Oliver Watts, Korin Richmond, Gustav Eje Henter
Publikováno v:
Valentini-Botinhao, C, Ribeiro, M S, Watts, O, Richmond, K & Eje Henter, G 2022, Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks . in H Ko & J H L Hansen (eds), Proceedings of Interspeech 2022 . pp. 471-475, Interspeech 2022, Incheon, Korea, Democratic People's Republic of, 18/09/22 . https://doi.org/10.21437/Interspeech.2022-10132
Automatically predicting the outcome of subjective listening tests is a challenging task. Ratings may vary from person to person even if preferences are consistent across listeners. While previous work has focused on predicting listeners' ratings (me
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f87893a6a35973d540b30a8388ba01a0
https://doi.org/10.21437/interspeech.2022-10132
https://doi.org/10.21437/interspeech.2022-10132
Publikováno v:
Interspeech 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea1afe5a04d30bdd2200de0557d14021
https://doi.org/10.21437/interspeech.2022-10138
https://doi.org/10.21437/interspeech.2022-10138
Publikováno v:
Webber, J, Valentini Botinhao, C, Williams, E, Eje Henter, G & King, S 2023, Autovocoder: fast waveform generation from a learned speech representation using differentiable digital signal processing . in ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 4/06/23 . https://doi.org/10.1109/ICASSP49357.2023.10095729
Most state-of-the-art Text-to-Speech systems use the mel-spectrogram as an intermediate representation, to decompose the task into acoustic modelling and waveform generation. A mel-spectrogram is extracted from the waveform by a simple, fast DSP oper
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2d0d1f81550068e6a8318688559d85d
Autor:
Zerrin Yumak, Taras Kucherenko, Pieter Wolfert, Gustav Eje Henter, Patrik Jonell, Youngwoo Yoon
Publikováno v:
ICMI
Embodied agents benefit from using non-verbal behavior when communicating with humans. Despite several decades of non-verbal behavior-generation research, there is currently no well-developed benchmarking culture in the field. For example, most resea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c821f02a182bbe49bd6c5008e8f13b9
https://doi.org/10.1145/3462244.3480983
https://doi.org/10.1145/3462244.3480983
Autor:
Patrik Jonell, Hedvig Kjellström, Gustav Eje Henter, Rajmund Nagy, Taras Kucherenko, Michael Neff
Publikováno v:
IVA
We propose a new framework for gesture generation, aiming to allow data-driven approaches to produce more semantically rich gestures. Our approach first predicts whether to gesture, followed by a prediction of the gesture properties. Those properties
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a42dfd31a5db280591b7bf4dfbffd172
http://arxiv.org/abs/2106.14736
http://arxiv.org/abs/2106.14736
Embodied human communication encompasses both verbal (speech) and non-verbal information (e.g., gesture and head movements). Recent advances in machine learning have substantially improved the technologies for generating synthetic versions of both of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::282921ebfb485617fcd30fe63248743e
http://arxiv.org/abs/2101.05684
http://arxiv.org/abs/2101.05684