MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914049363542016 |
|---|---|
| author | Avram, Andrei-Marius Bănescu, Ema-Ioana Robea, Anda-Teodora Cercel, Dumitru-Clementin Cercel, Mihaela-Claudia |
| author_facet | Avram, Andrei-Marius Bănescu, Ema-Ioana Robea, Anda-Teodora Cercel, Dumitru-Clementin Cercel, Mihaela-Claudia |
| contents | This paper introduces MoRoVoc, the largest dataset for analyzing the regional variation of spoken Romanian. It has more than 93 hours of audio and 88,192 audio samples, balanced between the Romanian language spoken in Romania and the Republic of Moldova. We further propose a multi-target adversarial training framework for speech models that incorporates demographic attributes (i.e., age and gender of the speakers) as adversarial targets, making models discriminative for primary tasks while remaining invariant to secondary attributes. The adversarial coefficients are dynamically adjusted via meta-learning to optimize performance. Our approach yields notable gains: Wav2Vec2-Base achieves 78.21% accuracy for the variation identification of spoken Romanian using gender as an adversarial target, while Wav2Vec2-Large reaches 93.08% accuracy for gender classification when employing both dialect and age as adversarial objectives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16781 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language Avram, Andrei-Marius Bănescu, Ema-Ioana Robea, Anda-Teodora Cercel, Dumitru-Clementin Cercel, Mihaela-Claudia Computation and Language This paper introduces MoRoVoc, the largest dataset for analyzing the regional variation of spoken Romanian. It has more than 93 hours of audio and 88,192 audio samples, balanced between the Romanian language spoken in Romania and the Republic of Moldova. We further propose a multi-target adversarial training framework for speech models that incorporates demographic attributes (i.e., age and gender of the speakers) as adversarial targets, making models discriminative for primary tasks while remaining invariant to secondary attributes. The adversarial coefficients are dynamically adjusted via meta-learning to optimize performance. Our approach yields notable gains: Wav2Vec2-Base achieves 78.21% accuracy for the variation identification of spoken Romanian using gender as an adversarial target, while Wav2Vec2-Large reaches 93.08% accuracy for gender classification when employing both dialect and age as adversarial objectives. |
| title | MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.16781 |