MELD-ST: An Emotion-aware Speech Translation Dataset
It addresses the problem of incorporating emotion into speech translation for better cross-lingual communication, but it is incremental as it builds on existing datasets and models.
The paper introduces the MELD-ST dataset for emotion-aware speech translation, containing English-to-Japanese and English-to-German pairs with about 10,000 utterances each annotated with emotion labels, and shows that fine-tuning with emotion labels can improve translation performance in some settings.
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.