1 citations · 1 across the 2 of their papers we have counts for
3 papers · 1 filter
Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search
Ben Hayes, Haokun Tian, Stefan Lattner
Sound matching can be formulated as optimizing synthesizer parameters against an audio-domain objective. However, objectives derived from generic audio representations are often di…
Assessing the Alignment of Audio Representations with Timbre Similarity Ratings
Haokun Tian, Stefan Lattner, Charalampos Saitis
Psychoacoustical so-called "timbre spaces" map perceptual similarity ratings of instrument sounds onto low-dimensional embeddings via multidimensional scaling, but suffer from scal…
Hybrid Losses for Hierarchical Embedding Learning
Haokun Tian, Stefan Lattner, Brian McFee +1
In traditional supervised learning, the cross-entropy loss treats all incorrect predictions equally, ignoring the relevance or proximity of wrong labels to the correct answer. By l…