A CVAE-based voice conversion method with a non-speech-specific preprocessing pipeline converts human speech to diverse animal and designed sounds at 44.1 kHz, improving similarity and quality over prior dog-only converters.
It accu- rately captured transient-rich signals and wide-frequency–range of non-human sounds
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds
A CVAE-based voice conversion method with a non-speech-specific preprocessing pipeline converts human speech to diverse animal and designed sounds at 44.1 kHz, improving similarity and quality over prior dog-only converters.