Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Pallavi Baljekar"'
Autor:
Julia Kreutzer, Isaac Caswell, Lisa Wang, Ahsan Wahab, Daan van Esch, Nasanbayar Ulzii-Orshikh, Allahsera Tapo, Nishant Subramani, Artem Sokolov, Claytone Sikasote, Monang Setyawan, Supheakmungkol Sarin, Sokhar Samb, Benoît Sagot, Clara Rivera, Annette Rios, Isabel Papadimitriou, Salomey Osei, Pedro Ortiz Suarez, Iroro Orife, Kelechi Ogueji, Andre Niyongabo Rubungo, Toan Q. Nguyen, Mathias Müller, André Müller, Shamsuddeen Hassan Muhammad, Nanda Muhammad, Ayanda Mnyakeni, Jamshidbek Mirzakhalov, Tapiwanashe Matangira, Colin Leong, Nze Lawson, Sneha Kudugunta, Yacine Jernite, Mathias Jenny, Orhan Firat, Bonaventure F. P. Dossou, Sakhile Dlamini, Nisansa de Silva, Sakine Çabuk Ballı, Stella Biderman, Alessia Battisti, Ahmed Baruwa, Ankur Bapna, Pallavi Baljekar, Israel Abebe Azime, Ayodele Awokoya, Duygu Ataman, Orevaoghene Ahia, Oghenefego Ahia, Sweta Agrawal, Mofetoluwa Adeyemi
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 10 (2023)
Externí odkaz:
https://doaj.org/article/183709a1b69d42379e0bf5e2c5ba1497
Autor:
Hansa Srinivasan, James Atwood, Alexander D'Amour, Yoni Halpern, D. Sculley, Pallavi Baljekar
Publikováno v:
FAT*
As machine learning becomes increasingly incorporated within high impact decision ecosystems, there is a growing need to understand the long-term behaviors of deployed ML-based decision systems and their potential consequences. Most approaches to und
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c2785a606d565f2cff6708e02b2aa8b
https://doi.org/10.1145/3351095.3372878
https://doi.org/10.1145/3351095.3372878
Autor:
Weimin Wang, Roman A. Solovyev, Igor Ivanov, Pavel Ostyakov, Sergey I. Nikolenko, D. Sculley, Yoni Halpern, Pallavi Baljekar, Miha Skalic, James Atwood, Eric Breck
Publikováno v:
The NeurIPS '18 Competition ISBN: 9783030291341
Popular large image classification datasets that are drawn from the web present Eurocentric and Americentric biases that negatively impact the generalizability of models trained on them Shreya Shankar et al. (No classification without representation:
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f99bb5317ce25a9bb78aaff036005ef
https://doi.org/10.1007/978-3-030-29135-8_6
https://doi.org/10.1007/978-3-030-29135-8_6
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e24f418583c5fd55d606b2034922ff04
https://doi.org/10.21437/interspeech.2018-1869
https://doi.org/10.21437/interspeech.2018-1869
Publikováno v:
ASRU
The paper describes Carnegie Mellon University's (CMU) entry to the ES-1 sub-task of the Blizzard Machine Learning Speech Synthesis Challenge 2017. The submitted system is a parametric model trained to predict vocoder parameters given linguistic feat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e0988343fb8fd6ef955a93f699ea51c
https://doi.org/10.1109/asru.2017.8268997
https://doi.org/10.1109/asru.2017.8268997
Autor:
Pallavi Baljekar, Alan W. Black
Publikováno v:
SSW
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::22abfbe2ef12b14e0ffcfb71893f5745
https://doi.org/10.21437/ssw.2016-30
https://doi.org/10.21437/ssw.2016-30
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b69c26fdd3279ac0efb9747ff488ee03
https://doi.org/10.21437/interspeech.2015-643
https://doi.org/10.21437/interspeech.2015-643
Publikováno v:
SLT
In this paper we introduce a simplified architecture for gated recurrent neural networks that can be used in single-pass applications, where word-spotting needs to be done in real-time and phoneme-level information is not available for training. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::abfaa09b21240e85c07ee55aac5ef04b
https://doi.org/10.1109/slt.2014.7078631
https://doi.org/10.1109/slt.2014.7078631
Autor:
Pallavi Baljekar, Hemant A. Patil
Publikováno v:
2012 International Conference on Signal Processing and Communications (SPCOM).
In this paper, a new feature-set, viz., Teager Energy Operator (TEO) phase has been proposed for automatic classification of normal vs. pathological voices. Development of TEO phase has been motivated from recently proposed linear prediction (LP) res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d274b7340cb35fca95f30c895fc7dd2f
https://doi.org/10.1109/spcom.2012.6289991
https://doi.org/10.1109/spcom.2012.6289991
Autor:
Hemant A. Patil, Pallavi Baljekar
Publikováno v:
ICASSP
In this paper, an attempt is made to compare and analyze the various waveform fractal dimension techniques for voice pathology classification. Three methods of estimating the fractal dimension directly from the time-domain waveform have been compared
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6eb62c325e0e8a429dd2755abcaf6697
https://doi.org/10.1109/icassp.2012.6288910
https://doi.org/10.1109/icassp.2012.6288910