KazEmoTTS: A Dataset for Kazakh Emotional Text-to-Speech Synthesis

research work·conference paper·active

LREC-COLING 2024 paper documenting the KazEmoTTS dataset and baseline synthesis model.

Verified facts

Official sitehttps://aclanthology.org/2024.lrec-main.841/
GeographyKazakhstan / Kazakh language
arxiv2404.01033
acl anthology2024.lrec-main.841
venueLREC-COLING 2024
dedupe risklow
discovery routemultilingual primary-source discovery
research topicsemotional TTS; Kazakh speech synthesis; audio dataset
proposed subtypeconference_paper
evidence strengthstrong
recommended prompt06-research-works
proposed entity typeResearchWork
classification rationaleMaterial AI-music, audio-AI, MIR, dataset, or music-rights relevance is explicit in the cited source.

Current

documentsKazEmoTTS

Sources & changes

Is this yours? Claim this record →·See something wrong? Report a correction →