Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic links in README
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (0.2%) to scientific vocabulary
Last synced: 10 months ago
·
JSON representation
·
Repository
Basic Info
- Host: GitHub
- Owner: AlejandroCiuba
- Language: TeX
- Default Branch: main
- Size: 5.86 KB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Created about 1 year ago
· Last pushed about 1 year ago
Metadata Files
Citation
Owner
- Name: Alejandro Ciuba
- Login: AlejandroCiuba
- Kind: user
- Location: Pittsburgh
- Website: https://www.linkedin.com/in/alejandro-ciuba-4b40b01a2/
- Repositories: 4
- Profile: https://github.com/AlejandroCiuba
I am a current student at The University of Pittsburgh, Class of 2023. Main interests are linguistics, computer science, and game-design.
Citation (citations/pubs.bib)
@inproceedings{kesirajuStrategiesImprovingLow2023,
title = {Strategies for {{Improving Low Resource Speech}} to {{Text Translation Relying}} on {{Pre-trained ASR Models}}},
booktitle = {{{INTERSPEECH}} 2023},
author = {Kesiraju, Santosh and Sarva{\v s}, Marek and Pavl{\'i}{\v c}ek, Tom{\'a}{\v s} and Macaire, C{\'e}cile and \textbf{Ciuba}, \textbf{Alejandro}},
year = {2023},
month = aug,
publisher = {ISCA},
doi = {10.21437/interspeech.2023-2506},
abstract = {Paper evaluates the use of multilingual ASR models as the base model for low-resource language end-to-end speech translation. The paper first trains a multilingual model on six high-resource language pairs and then performs a last fine-tuning using only 300 hours of Tamashek speech to make a Tamashek to French speech translation system. They find their approach helped low-resource languages on the speech side, but potentially low-resource target languages could also benefit from this approach. They lastly simulated the effects of additional speech data by creating artificially low-resource datasets for English-to-Portuguese. They find models significantly improve between low- and medium-resource partitions, but not as much afterwards. The paper is a good reference on basic techniques to deploy when creating ASR systems for low-resource languages.},
copyright = {All rights reserved}
}
@techreport{larcherMultilingualSpeechSpeech2022,
title = {Multi-Lingual {{Speech}} to {{Speech Translation}} for {{Under-Resourced Languages}}},
author = {Larcher, Anthony and Est{\`e}ve, Yannick and Rouvier, Mickael and Tomashenko, Natalia and Duret, Jarod and Laperriere, Gaelle and Kesijaru, Santosh and Sarvas, Marek and Kohlova, Renata and Li, Henry and Laurent, Antoine and Gaudier, Thibault and Pelloin, Valentin and Thebaud, Thomas and Billard, Emmanuelle and Galibert, Olivier and Ribeiro, Swen and Diddee, Harshita and Khurana, Sameer and Besacier, Laurent and Calapodescu, Ioan and Stafylakis, Themos and Pavliceck, Tomas and Macaire, Cecile and \textbf{Ciuba}, \textbf{Alejandro} and Vickers, Peter and Vicente, Luis and Mingote, Victoria and Gimeno, Pablo},
year = {2022},
month = aug,
institution = {Le Mans Universit{\'e}},
copyright = {All rights reserved}
}
@techreport{larcherMultilingualSpeechSpeech2022_mod,
title = {Multi-Lingual {{Speech}} to {{Speech Translation}} for {{Under-Resourced Languages}}},
author = {Larcher, Anthony and Est{\`e}ve, Yannick and Rouvier, Mickael and Macaire, \dots Cecile and \textbf{Ciuba}, \textbf{Alejandro} and Vickers, Peter and Vicente, Luis and Mingote, Victoria and Gimeno, Pablo},
year = {2022},
month = aug,
institution = {Le Mans Universit{\'e}},
copyright = {All rights reserved}
}
GitHub Events
Total
- Delete event: 1
- Push event: 2
- Create event: 3
Last Year
- Delete event: 1
- Push event: 2
- Create event: 3