MELD-ST: An Emotion-aware Speech Translation Dataset.
Sirou ChenSakiko YahataShuichiro ShimizuZhengdong YangYihang LiChenhui ChuSadao KurohashiPublished in: CoRR (2024)
Keyphrases
- emotion recognition
- text to speech synthesis
- emotional state
- speech recognition
- machine translation
- emotional speech
- automatic speech recognition
- database
- benchmark datasets
- speech signal
- data sets
- broadcast news
- noisy environments
- neural network
- query translation
- speaker identification
- text to speech
- physiological signals
- speech synthesis
- spontaneous speech
- recognition engine
- information retrieval
- feature extraction