Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
| Autor: | Jansen, Aren, Ellis, Daniel P. W., Hershey, Shawn, Moore, R. Channing, Plakal, Manoj, Popat, Ashok C., Saurous, Rif A. |
|---|---|
| Rok vydání: | 2019 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on multimodal unsupervised learning (as infants) and active learning (as children). With this motivation, we present a learning framework for sound representation and recognition that combines (i) a self-supervised objective based on a general notion of unimodal and cross-modal coincidence, (ii) a clustering objective that reflects our need to impose categorical structure on our experiences, and (iii) a cluster-based active learning procedure that solicits targeted weak supervision to consolidate categories into relevant semantic classes. By training a combined sound embedding/clustering/classification network according to these criteria, we achieve a new state-of-the-art unsupervised audio representation and demonstrate up to a 20-fold reduction in the number of labels required to reach a desired classification performance. Comment: This extended version of a ICASSP 2020 submission under same title has an added figure and additional discussion for easier consumption |
| Databáze: | arXiv |
| Externí odkaz: |
|