Houjun Liu

Meghanani 2021

# ntj

DOI: 10.3389/fcomp.2021.624558


analyzed spontaneous speech transcripts (only!) from TD and AD patients with fastText and CNN; best was \(83.33\%\) acc.


  • threw the NLP kitchen sink to transcripts
    • fastText
    • CNN (with vary n-gram kernel 2,3,4,5 sizes)

Notable Methods

  • embeddings seaded by GloVe
  • fastText are much faster, but CNN won out

Key Figs

the qual results

PAR (participant), INV (investigator)


Hey look a review of the field: