Zobrazeno 1 - 10
of 99
pro vyhledávání: '"Del Rio, Miguel A"'
Autor:
Heuser, Annika, Kendall, Tyler, del Rio, Miguel, McNamara, Quinten, Bhandari, Nishchal, Miller, Corey, Jetté, Migüel
Common measures of accuracy used to assess the performance of automatic speech recognition (ASR) systems, as well as human transcribers, conflate multiple sources of error. Stylistic differences, such as verbatim vs non-verbatim, can play a significa
Externí odkaz:
http://arxiv.org/abs/2409.03059
Publikováno v:
Sustainability 12:5003 (2020)
Tourism's increasing share of Gross Domestic Product throughout the world, its impact on employment and its continuous growth justifies the interest it raises amongst entrepreneurs and public authorities. However, this growth coexists with intense co
Externí odkaz:
http://arxiv.org/abs/2401.13679
Modern automatic speech recognition (ASR) systems have achieved superhuman Word Error Rate (WER) on many common corpora despite lacking adequate performance on speech in the wild. Beyond that, there is a lack of real-world, accented corpora to proper
Externí odkaz:
http://arxiv.org/abs/2203.15591
Publikováno v:
In The International Journal of Management Education March 2024 22(1)
Autor:
Del Rio, Miguel, Delworth, Natalie, Westerman, Ryan, Huang, Michelle, Bhandari, Nishchal, Palakapilly, Joseph, McNamara, Quinten, Dong, Joshua, Zelasko, Piotr, Jette, Miguel
Commonly used speech corpora inadequately challenge academic and commercial ASR systems. In particular, speech corpora lack metadata needed for detailed analysis and WER measurement. In response, we present Earnings-21, a 39-hour corpus of earnings c
Externí odkaz:
http://arxiv.org/abs/2104.11348
Autor:
Hinsvark, Arthur, Delworth, Natalie, Del Rio, Miguel, McNamara, Quinten, Dong, Joshua, Westerman, Ryan, Huang, Michelle, Palakapilly, Joseph, Drexler, Jennifer, Pirkin, Ilya, Bhandari, Nishchal, Jette, Miguel
Automatic Speech Recognition (ASR) systems generalize poorly on accented speech. The phonetic and linguistic variability of accents present hard challenges for ASR systems today in both data collection and modeling strategies. The resulting bias in A
Externí odkaz:
http://arxiv.org/abs/2104.10747
While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear what aspects of sentence-l
Externí odkaz:
http://arxiv.org/abs/2104.07578
Autor:
Mamou, Jonathan, Le, Hang, Del Rio, Miguel, Stephenson, Cory, Tang, Hanlin, Kim, Yoon, Chung, SueYeon
Deep neural networks (DNNs) have shown much empirical success in solving perceptual tasks across various cognitive modalities. While they are only loosely inspired by the biological brain, recent studies report considerable similarities between repre
Externí odkaz:
http://arxiv.org/abs/2006.01095
Autor:
Unzué, Leire, García, Eulogio, del Río, Miguel Rodríguez, Osende, Julio, Teijeiro-Mestre, Rodrigo, Fernandez-Friera, Leticia
Publikováno v:
In Cardiovascular Revascularization Medicine May 2023
Autor:
Unzué, Leire, García, Eulogio, Teijeiro, Rodrigo, del Río, Miguel Rodríguez, Díaz-Antón, Belén, Rodrigo, Francisco José Rodríguez, Parra, Francisco Javier
Publikováno v:
In Cardiovascular Revascularization Medicine February 2021 23:94-99