Voice conversion data augmentation and non-timbral embeddings raise automatic accent identification to a new state-of-the-art F1 of 0.66 on GenAID while supporting accent-controlled TTS.
Spoken lan- guage identification with phonotactics methods on minangk- abau, sundanese, and javanese languages,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Accent Identification via Voice Conversion and Non-Timbral Embeddings
Voice conversion data augmentation and non-timbral embeddings raise automatic accent identification to a new state-of-the-art F1 of 0.66 on GenAID while supporting accent-controlled TTS.