Authors propose ESS-CLAP and RA-CLAP, contrastive speech-text models for emotional speaking style retrieval, evaluated on PromptSpeech, TextrolSpeech, and SpeechCraft.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RA-CLAP: Relation-Augmented Emotional Speaking Style Contrastive Language-Audio Pretraining For Speech Retrieval
Authors propose ESS-CLAP and RA-CLAP, contrastive speech-text models for emotional speaking style retrieval, evaluated on PromptSpeech, TextrolSpeech, and SpeechCraft.