Zobrazeno 1 - 10
of 40 232
pro vyhledávání: '"Esteve, A."'
Speech encoders pretrained through self-supervised learning (SSL) have demonstrated remarkable performance in various downstream tasks, including Spoken Language Understanding (SLU) and Automatic Speech Recognition (ASR). For instance, fine-tuning SS
Externí odkaz:
http://arxiv.org/abs/2407.04533
Autor:
Ravanelli, Mirco, Parcollet, Titouan, Moumen, Adel, de Langen, Sylvain, Subakan, Cem, Plantinga, Peter, Wang, Yingzhi, Mousavi, Pooneh, Della Libera, Luca, Ploujnikov, Artem, Paissan, Francesco, Borra, Davide, Zaiem, Salah, Zhao, Zeyu, Zhang, Shucong, Karakasidis, Georgios, Yeh, Sung-Lin, Rouhe, Aku, Braun, Rudolf, Mai, Florian, Zuluaga-Gomez, Juan, Mousavi, Seyed Mahed, Nautsch, Andreas, Liu, Xuechen, Sagar, Sangeet, Duret, Jarod, Mdhaffar, Salima, Laperriere, Gaelle, De Mori, Renato, Esteve, Yannick
SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech recognition, speech enhancement, speaker recognition, text-to-speech, and much more. It promotes transparency and
Externí odkaz:
http://arxiv.org/abs/2407.00463
Autor:
Esteve-Paredes, J. J., García-Blázquez, M. A., Uría-Álvarez, A. J., Camarasa-Gómez, M., Palacios, J. J.
It is well-known that exciton effects are determinant to understand the optical absorption spectrum of low-dimensional materials. However, the role of excitons in nonlinear optical responses has been much less investigated at an experimental level. A
Externí odkaz:
http://arxiv.org/abs/2406.14215
Publikováno v:
27th International Conference on Text, Speech and Dialogue, Sep 2024, Brno (R{\'e}p. Tch{\`e}que), Czech Republic
In spoken Task-Oriented Dialogue (TOD) systems, the choice of the semantic representation describing the users' requests is key to a smooth interaction. Indeed, the system uses this representation to reason over a database and its domain knowledge to
Externí odkaz:
http://arxiv.org/abs/2406.13269
Self-Supervised Learning is vastly used to efficiently represent speech for Spoken Language Understanding, gradually replacing conventional approaches. Meanwhile, textual SSL models are proposed to encode language-agnostic semantics. SAMU-XLSR framew
Externí odkaz:
http://arxiv.org/abs/2406.12141
We present a simple algorithm to approximate the viscosity solution of Hamilton-Jacobi~(HJ) equations by means of an artificial deep neural network. The algorithm uses a stochastic gradient descent-based algorithm to minimize the least square princip
Externí odkaz:
http://arxiv.org/abs/2406.10758
Autor:
Contreras, T., Palmeiro, B., Almazán, H., Para, A., Martínez-Lema, G., Guenette, R., Adams, C., Álvarez, V., Aparicio, B., Aranburu, A. I., Arazi, L., Arnquist, I. J., Auria-Luna, F., Ayet, S., Azevedo, C. D. R., Bailey, K., Ballester, F., del Barrio-Torregrosa, M., Bayo, A., Benlloch-Rodríguez, J. M., Borges, F. I. G. M., Brodolin, A., Byrnes, N., Cárcel, S., Castillo, A., Cebrián, S., Church, E., Cid, L., Conde, C. A. N., Cossío, F. P., Dey, E., Díaz, G., Dickel, T., Echevarria, C., Elorza, M., Escada, J., Esteve, R., Felkai, R., Fernandes, L. M. P., Ferrario, P., Ferreira, A. L., Foss, F. W., Freixa, Z., García-Barrena, J., Gómez-Cadenas, J. J., González, R., Grocott, J. W. R., Hauptman, J., Henriques, C. A. O., Morata, J. A. Hernando, Herrero-Gómez, P., Herrero, V., Carrete, C. Hervés, Ifergan, Y., Jones, B. J. P., Kellerer, F., Larizgoitia, L., Larumbe, A., Lebrun, P., Lopez, F., López-March, N., Madigan, R., Mano, R. D. P., Marques, A. P., Martín-Albo, J., Martínez-Vara, M., Miller, R. L., Mistry, K., Molina-Canteras, J., Monrabal, F., Monteiro, C. M. B., Mora, F. J., Navarro, K. E., Novella, P., Nuñez, A., Nygren, D. R., Oblak, E., Palacio, J., Parmaksiz, I., Pazos, A., Pelegrin, J., Maneiro, M. Pérez, Querol, M., Redwine, A. B., Renner, J., Rivilla, I., Rogero, C., Rogers, L., Romeo, B., Romo-Luque, C., Santos, F. P., Santos, J. M. F. dos, Seemann, M., Shomroni, I., Silva, P. A. O. C., Simón, A., Soleti, S. R., Sorel, M., Soto-Oton, J., Teixeira, J. M. R., Teruel-Pardo, S., Toledo, J. F., Tonnelé, C., Torrent, J., Trettin, A., Usón, A., Valle, P. R. G., Veloso, J. F. C. A., Waiton, J., Yubero-Navarro, A.
The NEXT-White detector, a high-pressure gaseous xenon time projection chamber, demonstrated the excellence of this technology for future neutrinoless double beta decay searches using photomultiplier tubes (PMTs) to measure energy and silicon photomu
Externí odkaz:
http://arxiv.org/abs/2405.20427
Autor:
Zhang, Fan, Esteve-Yagüe, Carlos, Dittmer, Sören, Schönlieb, Carola-Bibiane, Roberts, Michael
Federated Learning (FL) enables collaborative training of machine learning models on decentralized data while preserving data privacy. However, data across clients often differs significantly due to class imbalance, feature distribution skew, sample
Externí odkaz:
http://arxiv.org/abs/2405.19000
Autor:
NEXT Collaboration, Byrnes, N., Dey, E., Foss, F. W., Jones, B. J. P., Madigan, R., McDonald, A., Miller, R. L., Navarro, K. E., Norman, L. R., Nygren, D. R., Adams, C., Almazán, H., Álvarez, V., Aparicio, B., Aranburu, A. I., Arazi, L., Arnquist, I. J., Auria-Luna, F., Ayet, S., Azevedo, C. D. R., Barcelon, J. E., Bailey, K., Ballester, F., del Barrio-Torregrosa, M., Bayo, A., Benlloch-Rodríguez, J. M., Borges, F. I. G. M., Brodolin, A., Cárcel, S., Castillo, A., Cebrián, S., Church, E., Cid, L., Conde, C. A. N., Contreras, T., Cossío, F. P., Díaz, G., Dickel, T., Echevarria, C., Elorza, M., Escada, J., Esteve, R., Felkai, R., Fernandes, L. M. P., Ferrario, P., Ferreira, A. L., Freixa, Z., García-Barrena, J., Gómez-Cadenas, J. J., González, R., Grocott, J. W. R., Guenette, R., Hauptman, J., Henriques, C. A. O., Morata, J. A. Hernando, Herrero-Gómez, P., Herrero, V., Carrete, C. Hervés, Ho, P., Ifergan, Y., Kellerer, F., Larizgoitia, L., Larumbe, A., Lebrun, P., Lopez, F., López-March, N., Mano, R. D. P., Marques, A. P., Martín-Albo, J., Martínez-Lema, G., Martínez-Vara, M., Mistry, K., Molina-Canteras, J., Monrabal, F., Monteiro, C. M. B., Mora, F. J., Novella, P., Nuñez, A., Oblak, E., Palacio, J., Palmeiro, B., Para, A., Parmaksiz, I., Pazos, A., Pelegrin, J., Maneiro, M. Pérez, Querol, M., Redwine, A. B., Renner, J., Rivilla, I., Rogero, C., Rogers, L., Romeo, B., Romo-Luque, C., Santos, F. P., Santos, J. M. F. dos, Seemann, M., Shomroni, I., Silva, P. A. O. C., Simón, A., Soleti, S. R., Sorel, M., Soto-Oton, J., Teixeira, J. M. R., Teruel-Pardo, S., Toledo, J. F., Tonnelé, C., Torrent, J., Trettin, A., Usón, A., Valle, P. R. G., Veloso, J. F. C. A., Waiton, J., Yubero-Navarro, A.
The imaging of individual Ba$^{2+}$ ions in high pressure xenon gas is one possible way to attain background-free sensitivity to neutrinoless double beta decay and hence establish the Majorana nature of the neutrino. In this paper we demonstrate sele
Externí odkaz:
http://arxiv.org/abs/2406.15422
Autor:
Sekkat, Chloé, Leroy, Fanny, Mdhaffar, Salima, Smith, Blake Perry, Estève, Yannick, Dureau, Joseph, Coucke, Alice
Recent works demonstrate that voice assistants do not perform equally well for everyone, but research on demographic robustness of speech technologies is still scarce. This is mainly due to the rarity of large datasets with controlled demographic tag
Externí odkaz:
http://arxiv.org/abs/2405.19342