Fully Unsupervised Topic Clustering of Unlabelled Spoken Audio Using Self-Supervised Representation Learning and Topic Model.
Takashi MaekakuYuya FujitaXuankai ChangShinji WatanabePublished in: ICASSP (2023)
Keyphrases
- topic models
- latent dirichlet allocation
- weakly supervised
- topic discovery
- topic modeling
- unsupervised learning
- clustering algorithm
- active learning
- multimedia
- generative model
- probabilistic model
- text mining
- latent topics
- fully unsupervised
- probabilistic topic models
- learning algorithm
- baseline models
- image classification
- co occurrence
- learning tasks
- lda model
- microblog posts