35 citations · 121 across the 18 of their papers we have counts for
7 papers · 1 filter
On the Informativeness of Supervision Signals
Ilia Sucholutsky, Ruairidh M. Battleday, Katherine M. Collins +7
Supervised learning typically focuses on learning transferable representations from training examples annotated by humans. While rich annotations (like soft labels) carry more info…
Analyzing Diffusion as Serial Reproduction
Raja Marjieh, Ilia Sucholutsky, Thomas A. Langlois +2
Diffusion models are a class of generative models that learn to synthesize samples by inverting a diffusion process that gradually maps data into noise. While these models have enj…
Words are all you need? Language as an approximation for human similarity judgments
Raja Marjieh, Pol van Rijn, Ilia Sucholutsky +4
Human similarity judgments are a powerful supervision signal for machine learning applications based on techniques such as contrastive learning, information retrieval, and model al…
Bridging the prosody GAP: Genetic Algorithm with People to efficiently sample emotional prosody
Pol van Rijn, Harin Lee, Nori Jacoby
The human voice effectively communicates a range of emotions with nuanced variations in acoustics. Existing emotional speech corpora are limited in that they are either (a) highly…
WavThruVec: Latent speech representation as intermediate features for neural speech synthesis
Hubert Siuzdak, Piotr Dura, Pol van Rijn +1
Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms. Howeve…
VoiceMe: Personalized voice generation in TTS
Pol van Rijn, Silvan Mertes, Dominik Schiller +5
Novel text-to-speech systems can generate entirely new voices that were not seen during training. However, it remains a difficult task to efficiently create personalized voices fro…
Predicting Human Similarity Judgments Using Large Language Models
Raja Marjieh, Ilia Sucholutsky, Theodore R. Sumers +2
Similarity judgments provide a well-established method for accessing mental representations, with applications in psychology, neuroscience and machine learning. However, collecting…