Ismail Rasim Ulgen
PulseAugur coverage of Ismail Rasim Ulgen — every cluster mentioning Ismail Rasim Ulgen across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New sub-center modeling enhances speech generation variability
Researchers have developed a new sub-center modeling framework for speaker embeddings in speech generation. This approach moves away from single-prototype representations, learning multiple sub-centers to better capture…
-
New research explores cross-lingual prosody similarity in speech translation
A new research paper analyzes prosody similarity across different languages, focusing on English, German, Spanish, and French. The study investigates how pitch, energy, and temporal features in speech translation correl…
-
DiffAnon offers diffusion-based voice anonymization with controllable prosody
Researchers have developed DiffAnon, a novel diffusion-based method for voice anonymization that offers fine-grained control over prosody preservation. This approach allows for a continuous trade-off between anonymizati…