MELD-ST: An Emotion-aware Speech Translation Dataset.
Sirou ChenSakiko YahataShuichiro ShimizuZhengdong YangYihang LiChenhui ChuSadao KurohashiPublished in: ACL (Findings) (2024)
Keyphrases
- emotion recognition
- text to speech synthesis
- speech recognition
- emotional state
- benchmark datasets
- emotional speech
- machine translation
- automatic speech recognition
- speech synthesis
- audio visual
- database
- facial expressions
- english words
- synthetic datasets
- virtual humans
- natural language processing
- speaker recognition
- text to speech
- user interface
- endpoint detection
- data sets