Identifying depression-related topics in smartphone-collected free-response speech recordings using an automatic speech recognition system and a deep learning topic model.
Yuezhou ZhangAmos A. FolarinJudith DineleyPauline CondeValeria de AngelShaoxiong SunYatharth RanjanZulqarnain RashidCallum L. StewartPetroula LaiouHeet SankesaraLinglong QianFaith MatchamKatie M. WhiteCarolin OetzmannFemke LamersSara SiddiSara SimblettBjörn W. SchullerSrinivasan VairavanTil WykesJosep Maria HaroBrenda W. J. H. PenninxVaibhav A. NarayanMatthew HotopfRichard JB DobsonNicholas CumminsRADAR-CNS ConsortiumPublished in: CoRR (2023)
Keyphrases
- topic models
- deep learning
- related topics
- weakly supervised
- latent dirichlet allocation
- topic modeling
- text mining
- unsupervised learning
- machine learning
- computer science
- co occurrence
- generative model
- probabilistic model
- latent variables
- pattern recognition
- image segmentation
- active learning
- hidden markov models
- natural language processing
- data mining
- dimensionality reduction
- training data
- learning algorithm