Avengers, Ensemble! Benefits of ensembling in grapheme-to-phoneme prediction
Vagrant Gautam, Wang Yau Li, Zafarullah Mahmood, Frederic Mailhot, Shreekantha Nadig, Riqiang Wang, Nathan Zhang
Abstract
We describe three baseline beating systems for the high-resource English-only sub-task of the SIGMORPHON 2021 Shared Task 1: a small ensemble that Dialpad’s speech recognition team uses internally, a well-known off-the-shelf model, and a larger ensemble model comprising these and others. We additionally discuss the challenges related to the provided data, along with the processing steps we took.- Anthology ID:
- 2021.sigmorphon-1.16
- Original:
- 2021.sigmorphon-1.16v1
- Version 2:
- 2021.sigmorphon-1.16v2
- Volume:
- Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venue:
- SIGMORPHON
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 141–147
- Language:
- URL:
- https://aclanthology.org/2021.sigmorphon-1.16
- DOI:
- 10.18653/v1/2021.sigmorphon-1.16
- Cite (ACL):
- Vagrant Gautam, Wang Yau Li, Zafarullah Mahmood, Frederic Mailhot, Shreekantha Nadig, Riqiang Wang, and Nathan Zhang. 2021. Avengers, Ensemble! Benefits of ensembling in grapheme-to-phoneme prediction. In Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 141–147, Online. Association for Computational Linguistics.
- Cite (Informal):
- Avengers, Ensemble! Benefits of ensembling in grapheme-to-phoneme prediction (Gautam et al., SIGMORPHON 2021)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2021.sigmorphon-1.16.pdf