Deep learning-based end-to-end spoken language identification system for domain-mismatched scenario

Woohyun Kang, Md Jahangir Alam, Abderrahim Fathan


Abstract
Domain mismatch is a critical issue when it comes to spoken language identification. To overcome the domain mismatch problem, we have applied several architectures and deep learning strategies which have shown good results in cross-domain speaker verification tasks to spoken language identification. Our systems were evaluated on the Oriental Language Recognition (OLR) Challenge 2021 Task 1 dataset, which provides a set of cross-domain language identification trials. Among our experimented systems, the best performance was achieved by using the mel frequency cepstral coefficient (MFCC) and pitch features as input and training the ECAPA-TDNN system with a flow-based regularization technique, which resulted in a Cavg of 0.0631 on the OLR 2021 progress set.
Anthology ID:
2022.lrec-1.798
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
7339–7343
Language:
URL:
https://aclanthology.org/2022.lrec-1.798
DOI:
Bibkey:
Cite (ACL):
Woohyun Kang, Md Jahangir Alam, and Abderrahim Fathan. 2022. Deep learning-based end-to-end spoken language identification system for domain-mismatched scenario. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 7339–7343, Marseille, France. European Language Resources Association.
Cite (Informal):
Deep learning-based end-to-end spoken language identification system for domain-mismatched scenario (Kang et al., LREC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lrec-1.798.pdf
Data
OLR 2021