EmoTale: An Enacted Speech-emotion Dataset in Danish
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913998568423424 |
|---|---|
| author | Hjuler, Maja J. Skat-Rørdam, Harald V. Clemmensen, Line H. Das, Sneha |
| author_facet | Hjuler, Maja J. Skat-Rørdam, Harald V. Clemmensen, Line H. Das, Sneha |
| contents | While multiple emotional speech corpora exist for commonly spoken languages, there is a lack of functional datasets for smaller (spoken) languages, such as Danish. To our knowledge, Danish Emotional Speech (DES), published in 1997, is the only other database of Danish emotional speech. We present EmoTale; a corpus comprising Danish and English speech recordings with their associated enacted emotion annotations. We demonstrate the validity of the dataset by investigating and presenting its predictive power using speech emotion recognition (SER) models. We develop SER models for EmoTale and the reference datasets using self-supervised speech model (SSLM) embeddings and the openSMILE feature extractor. We find the embeddings superior to the hand-crafted features. The best model achieves an unweighted average recall (UAR) of 64.1% on the EmoTale corpus using leave-one-speaker-out cross-validation, comparable to the performance on DES. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14548 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EmoTale: An Enacted Speech-emotion Dataset in Danish Hjuler, Maja J. Skat-Rørdam, Harald V. Clemmensen, Line H. Das, Sneha Computation and Language Sound Audio and Speech Processing While multiple emotional speech corpora exist for commonly spoken languages, there is a lack of functional datasets for smaller (spoken) languages, such as Danish. To our knowledge, Danish Emotional Speech (DES), published in 1997, is the only other database of Danish emotional speech. We present EmoTale; a corpus comprising Danish and English speech recordings with their associated enacted emotion annotations. We demonstrate the validity of the dataset by investigating and presenting its predictive power using speech emotion recognition (SER) models. We develop SER models for EmoTale and the reference datasets using self-supervised speech model (SSLM) embeddings and the openSMILE feature extractor. We find the embeddings superior to the hand-crafted features. The best model achieves an unweighted average recall (UAR) of 64.1% on the EmoTale corpus using leave-one-speaker-out cross-validation, comparable to the performance on DES. |
| title | EmoTale: An Enacted Speech-emotion Dataset in Danish |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2508.14548 |