Deep learning-based expressive speech synthesis: a systematic review of approaches, challenges, and resources

EURASIP Journal on Audio, Speech, and Music Processing

Table 6 List of main open source expressive TTS databases according to publications reviewed in this work

Database	Language	Multi Emotion	Multi Speaker
Blizzard Challenge 2012, 2013, 2016, 2019	English
VCTK	English		\(\checkmark\)
LibriSpeech	English		\(\checkmark\)
IEMOCAP	English	\(\checkmark\)	\(\checkmark\)
CMU ARCTIC	English		\(\checkmark\)
LJSpeech	English
LibriTTS	English		\(\checkmark\)
Chinese Standard Mandarin Speech Copus(CSMSC)	Mandarin Chinese
Aishell-3	Mandarin Chinese
Korean Emotional Speech (KES) dataset	Korean	\(\checkmark\)
English conversation corpus (ECC)	English		\(\checkmark\)
IndicTTS database	Indian
Emotional Speech Dataset (ESD)	English/Mandarin Chinese	\(\checkmark\)	\(\checkmark\)
Japanese Kamishibai and audiobook corpus (J-KAC)	Japanese
Multilingual LibriSpeech	Multilingual		\(\checkmark\)
Korean Single Speaker (KSS)	Korean		\(\checkmark\)