Zobrazeno 1 - 9 of 9 pro vyhledávání: '"Leila Ben Letaifa"'
1
Akademický článek
Variable Scale Pruning for Transformer Model Compression in End-to-End Speech Recognition
Autor: Leila Ben Letaifa, Jean-Luc Rouas
Publikováno v: Algorithms, Vol 16, Iss 9, p 398 (2023)
Transformer models are being increasingly used in end-to-end speech recognition systems for their performance. However, their substantial size poses challenges for deploying them in real-world applications. These models heavily rely on attention and
Externí odkaz: https://doaj.org/article/3b78213a31714f75b31ae8e0168dea02
Zobrazit plný text záznamu
2
Akademický článek
Perceptual Borderline for Balancing Multi-Class Spontaneous Emotional Data
Autor: Leila Ben Letaifa, M. Ines Torres
Publikováno v: IEEE Access, Vol 9, Pp 55939-55954 (2021)
Speech is a behavioural biometric signal that can provide important information to understand the human intends as well as their emotional status. The paper is centered on the speech-based identification of the seniors’s emotional status during the
Externí odkaz: https://doaj.org/article/7ef90a0d085349ec903cb55c4b378bb0
Zobrazit plný text záznamu
3
Fine-grained analysis of the transformer model for efficient pruning
Autor: Leila Ben Letaifa, Jean-Luc Rouas
Publikováno v: 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)
2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA), Dec 2022, Nassau, Bahamas. pp.897-902, ⟨10.1109/ICMLA55696.2022.00149⟩
In automatic speech recognition, deep learning models such as transformers are increasingly used for their high performance. However, they suffer from their large size, which makes it very difficult to use them in real contexts. Hence the idea of pru
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24be8e62830cf44ba3efacc37bc3a2a6
https://hal.science/hal-04047338/file/conference_101719.pdf
Zobrazit plný text záznamu
6
A Spanish Corpus for Talking to the Elderly
Autor: Mikel deVelasco, M. Inés Torres, Leila Ben Letaifa, Alain Vázquez, Javier Mikel Olaso, Asier López-Zorrilla, Raquel Justo
Publikováno v: Addi. Archivo Digital para la Docencia y la Investigación
instname
Lecture Notes in Electrical Engineering
Lecture Notes in Electrical Engineering-Conversational Dialogue Systems for the Next Decade
Addi: Archivo Digital para la Docencia y la Investigación
Universidad del País Vasco
Lecture Notes in Electrical Engineering ISBN: 9789811583940
IWSDS
Paper presented at 11th International Workshop on Spoken Dialogue Systems, IWSDS 2020; Madrid; Spain; 21 September 2020 through 23 September 2020 In this work, a Spanish corpus that was developed, within the EMPATHIC project (http://www.empathic-proj
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f3cbf6723cbe7a214aa3170672c412bc
http://hdl.handle.net/10810/50021
Zobrazit plný text záznamu
7
Perceptual Borderline for Balancing Multi-Class Spontaneous Emotional Data
Autor: Leila Ben Letaifa, M. Ines Torres
Publikováno v: Addi: Archivo Digital para la Docencia y la Investigación
Universidad del País Vasco
IEEE Access
Addi. Archivo Digital para la Docencia y la Investigación
instname
IEEE Access, 2021, 9, pp.55939-55954. ⟨10.1109/ACCESS.2021.3071485⟩
IEEE Access, Vol 9, Pp 55939-55954 (2021)
Speech is a behavioural biometric signal that can provide important information to understand the human intends as well as their emotional status. The paper is centered on the speech-based identification of the seniors’s emotional status during the
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::62ad61c443e72a7306f8686fdfe30dfc
Zobrazit plný text záznamu
8
Adding dimensional features for emotion recognition on speech
Autor: María Inés Torres, Leila Ben Letaifa, Raquel Justo
Publikováno v: 2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)
Addi. Archivo Digital para la Docencia y la Investigación
instname
ATSIP
Addi: Archivo Digital para la Docencia y la Investigación
Universidad del País Vasco
Developing accurate emotion recognition systems requires extracting suitable features of these emotions. In this paper, we propose an original approach of parameters extraction based on the strong, theoretical and empirical, correlation between the e
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6d73fc18b31e8edd5bc78df6fceabd02
Zobrazit plný text záznamu
9
Contrasting the Emotions identified in Spanish TV debates and in Human-Machine Interactions
Autor: Midel de Velasco, M. Inés Torres, Leila Ben Letaifa, Raquel Justo
Publikováno v: IberSPEECH 2021
IberSPEECH
Addi. Archivo Digital para la Docencia y la Investigación
instname
Addi: Archivo Digital para la Docencia y la Investigación
Universidad del País Vasco
Conferencia presentada en IberSPEECH 2021, 24-25 March 2021, Valladolid, Spain This work is aimed to contrast the similarities and differences for the emotions identified in two very different scenarios: human-to-human interaction on Spanish TV debat
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f1ed0696071329ff2e15cd0a9ab909e
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje