End-to-End Speech Translation for Code Switched Speech

Orion Weller, Matthias Sperber, Telmo Pires, Hendra Setiawan, Christian Gollan, Dominic Telaar, Matthias Paulik


Abstract
Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages. CS can pose significant accuracy challenges to NLP, due to the often monolingual nature of the underlying systems. In this work, we focus on CS in the context of English/Spanish conversations for the task of speech translation (ST), generating and evaluating both transcript and translation. To evaluate model performance on this task, we create a novel ST corpus derived from existing public data sets. We explore various ST architectures across two dimensions: cascaded (transcribe then translate) vs end-to-end (jointly transcribe and translate) and unidirectional (source -> target) vs bidirectional (source <-> target). We show that our ST architectures, and especially our bidirectional end-to-end architecture, perform well on CS speech, even when no CS training data is used.
Anthology ID:
2022.findings-acl.113
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venues:
ACL | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1435–1448
Language:
URL:
https://aclanthology.org/2022.findings-acl.113
DOI:
10.18653/v1/2022.findings-acl.113
Bibkey:
Cite (ACL):
Orion Weller, Matthias Sperber, Telmo Pires, Hendra Setiawan, Christian Gollan, Dominic Telaar, and Matthias Paulik. 2022. End-to-End Speech Translation for Code Switched Speech. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1435–1448, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
End-to-End Speech Translation for Code Switched Speech (Weller et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.113.pdf
Code
 apple/ml-code-switched-speech-translation
Data
CoVoST