Unsupervised Instance Discriminative Learning for Depression Detection from Speech Signals
Jinhan Wang, Vijay Ravi, Jonathan Flint, Abeer Alwan
Abstract
-value 0.0015 and 0.05, respectively, are observed using PIS in the detection of MDD relative to the baseline without pre-training.
Topics & Concepts
Discriminative modelComputer scienceArtificial intelligenceEmbeddingCluster analysisSpeech recognitionRandom forestSampling (signal processing)Pattern recognition (psychology)Unsupervised learningMachine learningNatural language processingFilter (signal processing)Computer visionVoice and Speech DisordersEmotion and Mood RecognitionSpeech Recognition and Synthesis