Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915846231687168 |
|---|---|
| author | Buitrago, Pol Pareras, Oriol Costa, Federico Hernando, Javier |
| author_facet | Buitrago, Pol Pareras, Oriol Costa, Federico Hernando, Javier |
| contents | Paralinguistic speech tasks are often considered relatively language-agnostic, as they rely on extralinguistic acoustic cues rather than lexical content. However, prior studies report performance degradation under cross-lingual conditions, indicating non-negligible language dependence. Still, these studies typically focus on isolated language pairs or task-specific settings, limiting comparability and preventing a systematic assessment of task-level language dependence.
We introduce the Cross-Lingual Transfer Matrix (CLTM), a systematic method to quantify cross-lingual interactions between pairs of languages within a given task. We apply the CLTM to two paralinguistic tasks, gender identification and speaker verification, using a multilingual HuBERT-based encoder, to analyze how donor-language data affects target-language performance during fine-tuning. Our results reveal distinct transfer patterns across tasks and languages, reflecting systematic, language-dependent effects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08231 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks Buitrago, Pol Pareras, Oriol Costa, Federico Hernando, Javier Audio and Speech Processing Computation and Language Paralinguistic speech tasks are often considered relatively language-agnostic, as they rely on extralinguistic acoustic cues rather than lexical content. However, prior studies report performance degradation under cross-lingual conditions, indicating non-negligible language dependence. Still, these studies typically focus on isolated language pairs or task-specific settings, limiting comparability and preventing a systematic assessment of task-level language dependence. We introduce the Cross-Lingual Transfer Matrix (CLTM), a systematic method to quantify cross-lingual interactions between pairs of languages within a given task. We apply the CLTM to two paralinguistic tasks, gender identification and speaker verification, using a multilingual HuBERT-based encoder, to analyze how donor-language data affects target-language performance during fine-tuning. Our results reveal distinct transfer patterns across tasks and languages, reflecting systematic, language-dependent effects. |
| title | Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks |
| topic | Audio and Speech Processing Computation and Language |
| url | https://arxiv.org/abs/2603.08231 |