MELD-ST: An Emotion-aware Speech Translation Dataset

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Sirou, Yahata, Sakiko, Shimizu, Shuichiro, Yang, Zhengdong, Li, Yihang, Chu, Chenhui, Kurohashi, Sadao
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929352212480000
author Chen, Sirou
Yahata, Sakiko
Shimizu, Shuichiro
Yang, Zhengdong
Li, Yihang
Chu, Chenhui
Kurohashi, Sadao
author_facet Chen, Sirou
Yahata, Sakiko
Shimizu, Shuichiro
Yang, Zhengdong
Li, Yihang
Chu, Chenhui
Kurohashi, Sadao
contents Emotion plays a crucial role in human conversation. This paper underscores the significance of considering emotion in speech translation. We present the MELD-ST dataset for the emotion-aware speech translation task, comprising English-to-Japanese and English-to-German language pairs. Each language pair includes about 10,000 utterances annotated with emotion labels from the MELD dataset. Baseline experiments using the SeamlessM4T model on the dataset indicate that fine-tuning with emotion labels can enhance translation performance in some settings, highlighting the need for further research in emotion-aware speech translation systems.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13233
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MELD-ST: An Emotion-aware Speech Translation Dataset
Chen, Sirou
Yahata, Sakiko
Shimizu, Shuichiro
Yang, Zhengdong
Li, Yihang
Chu, Chenhui
Kurohashi, Sadao
Computation and Language
Emotion plays a crucial role in human conversation. This paper underscores the significance of considering emotion in speech translation. We present the MELD-ST dataset for the emotion-aware speech translation task, comprising English-to-Japanese and English-to-German language pairs. Each language pair includes about 10,000 utterances annotated with emotion labels from the MELD dataset. Baseline experiments using the SeamlessM4T model on the dataset indicate that fine-tuning with emotion labels can enhance translation performance in some settings, highlighting the need for further research in emotion-aware speech translation systems.
title MELD-ST: An Emotion-aware Speech Translation Dataset
topic Computation and Language
url https://arxiv.org/abs/2405.13233