Introduces the MMEE corpus and shows multilingual training improves robustness of speech emphasis models across languages and emotions while monolingual models transfer poorly.
Emphasis rendering for conversational text-to-speech with multi-modal multi-scale con- text modeling,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do Speech Emphasis Models Generalize across Languages and Emotions?
Introduces the MMEE corpus and shows multilingual training improves robustness of speech emphasis models across languages and emotions while monolingual models transfer poorly.