Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Leonardo Pepino"'
Publikováno v:
Revista Elektrón, Vol 3, Iss 1, Pp 16-23 (2019)
Airborne acoustic insulation prediction models allow to evaluate the sound transmission loss of construction solutions in buildings. Among the different building materials used in constructions, homogeneous and isotropic materials of various thicknes
Externí odkaz:
https://doaj.org/article/75218ade97b14a2dac48aa4ee19fd05b
Publikováno v:
Building Acoustics. 29:349-366
Single-leaf panels made from homogeneous and isotropic materials are commonly used in buildings. However, it is often necessary to add various layers of the same or different materials in order to increase the acoustic insulation. This article presen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ede2ad7f95dcf0321058fc90b03aa84
https://doi.org/10.1177/1351010x221101969
https://doi.org/10.1177/1351010x221101969
Autor:
Lara Gauder, Leonardo Pepino, Pablo Riera, Silvina Brussino, Jazmín Vidal, Agustín Gravano, Luciana Ferrer
Publikováno v:
Computer Speech & Language. 80:101487
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79c057705298eee80295fffbec789e47
https://doi.org/10.1016/j.csl.2023.101487
https://doi.org/10.1016/j.csl.2023.101487
Transformers have revolutionized the world of deep learning, specially in the field of natural language processing. Recently, the Audio Spectrogram Transformer (AST) was proposed for audio classification, leading to state of the art results in severa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::999153c5b5dba02e9bf69d4136995adb
http://arxiv.org/abs/2110.06999
http://arxiv.org/abs/2110.06999
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4ebfc3737373eda0eded42de9c7a93ba
https://doi.org/10.21437/interspeech.2021-753
https://doi.org/10.21437/interspeech.2021-753
Publikováno v:
Interspeech 2021.
Emotion recognition datasets are relatively small, making the use of the more sophisticated deep learning approaches challenging. In this work, we propose a transfer learning method for speech emotion recognition where features extracted from pre-tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::38397505f54066ae9e7923c74b061bde
https://doi.org/10.21437/interspeech.2021-703
https://doi.org/10.21437/interspeech.2021-703
Autor:
Roberto Etchenique, Armando Ezequiel Puerta, Carolina Grillo Vidal, Sol Minoldo, Rodrigo Maidana, Ezequiel Pecker-Marcosig, Rodrigo Quiroga, Laouen Belloli, Guillermo Solovey, Mauricio Mendiluce, Rodrigo Goldsmit, Pablo Laciana, Juan E. Kamienkowski, Mariano Zapatero, Mario Lozano, Leonardo Boechi, Guillermo Durán, Leonardo Pepino, Esteban Omar Lanzarotti, Ana Maria Bianco, Luciana Ferrer, Rodrigo Castro, Diego Garbervetsky, Marina Valdora, Natalia Brenda Fernandez, Mehrnoosh Arrar
Publikováno v:
SEDICI (UNLP)
Universidad Nacional de La Plata
instacron:UNLP
CONICET Digital (CONICET)
Consejo Nacional de Investigaciones Científicas y Técnicas
instacron:CONICET
Universidad Nacional de La Plata
instacron:UNLP
CONICET Digital (CONICET)
Consejo Nacional de Investigaciones Científicas y Técnicas
instacron:CONICET
With the arrival of the pandemic in Argentina in March 2020, a working group of scientists from two institutes belonging to the Faculty of Exact and Natural Sciences of the University of Buenos Aires and CONICET, together with colleagues from differe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e27633a9a97fea8cb9f5f04cf271fc80
http://sedici.unlp.edu.ar/handle/10915/137753
http://sedici.unlp.edu.ar/handle/10915/137753
Publikováno v:
ICASSP
In this paper, we study different approaches for classifying emotions from speech using acoustic and text-based features. We propose to obtain contextualized word embeddings with BERT to represent the information contained in speech transcriptions an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ba3d5855ee2bdc7fa8f3a6499b7ebf94
https://doi.org/10.1109/icassp40776.2020.9054709
https://doi.org/10.1109/icassp40776.2020.9054709
Publikováno v:
Politecnico di Torino-IRIS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::5a22117c4467703a6f814fcfbcbc0ffb
https://iris.polito.it/handle/11583/2810214
https://iris.polito.it/handle/11583/2810214