COLA
2000년 도입 · 논문 32편에서 사용
COLA is a self-supervised pre-training approach for learning a general-purpose representation of audio. It is based on contrastive learning: it learns a representation which assigns high similarity to audio segments extracted from the same recording while assigning lower similarity to segments from different recordings.
출처: Contrastive Learning of General-Purpose Audio Representations
소개 논문: Contrastive Learning of General-Purpose Audio Representations
Self-Supervised Learning · GeneralGenerative Audio Models · Audio