Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Zhongdi Qu"'
Autor:
Benjamin Doerr, Zhongdi Qu
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031147203
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9748bcd65eb8ffba6a1ee371cbaf6d94
https://doi.org/10.1007/978-3-031-14721-0_28
https://doi.org/10.1007/978-3-031-14721-0_28
Autor:
Benjamin Doerr, Zhongdi Qu
Publikováno v:
IEEE Transactions on Evolutionary Computation. :1-1
Very recently, the first mathematical runtime analyses of the multi-objective evolutionary optimizer NSGA-II have been conducted. We continue this line of research with a first runtime analysis of this algorithm on a benchmark problem consisting of t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3d85bd0a05af007736b093a80c482a18
https://doi.org/10.1109/tevc.2023.3250552
https://doi.org/10.1109/tevc.2023.3250552
Publikováno v:
ASRU
Recent advances in end-to-end speech recognition have made it possible to build multilingual models, capable of recognizing speech in multiple languages. Multilingual models can outperform their monolingual counterparts, depending on the amount of tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::110b246adf13c06fdee5992e4097f166
https://doi.org/10.1109/asru46091.2019.9003870
https://doi.org/10.1109/asru46091.2019.9003870
Autor:
Arun Narayanan, Galen Chuang, Zhongdi Qu, Rohit Prabhavalkar, Neeraj Gaur, Parisa Haghani, Pedro J. Moreno, Michiel Bacchiani, Austin Waters
Publikováno v:
SLT
Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text (or top N hy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1b2db66c60a737a66d9d88c906e0de7
https://doi.org/10.1109/slt.2018.8639043
https://doi.org/10.1109/slt.2018.8639043
Publikováno v:
ASRU
We explore the feasibility of training long short-term memory (LSTM) recurrent neural networks (RNNs) with syllables, rather than phonemes, as outputs. Syllables are a natural choice of linguistic unit for modeling the acoustics of languages such as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9dc471d88bac930ac586102fd74268aa
https://doi.org/10.1109/asru.2017.8268932
https://doi.org/10.1109/asru.2017.8268932