eduzhai > Applied Sciences > Engineering >

Alzheimers Dementia Detection from Audio and Text Modalities

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Automatic detection of Alzheimer s dementia by speech processing is enhancedwhen features of both the acoustic waveform and the content are extracted.Audio and text transcription have been widely used in health-related tasks, asspectral and prosodic speech features, as well as semantic and linguisticcontent, convey information about various diseases. Hence, this paper describesthe joint work of the GTM-UVIGO research group and acceXible startup to theADDReSS challenge at INTERSPEECH 2020. The submitted systems aim to detectpatterns of Alzheimer s disease from both the patient s voice and messagetranscription. Six different systems have been built and compared: four of themare speech-based and the other two systems are text-based. The x-vector,i-vector, and statistical speech-based functionals features are evaluated. As alower speaking fluency is a common pattern in patients with Alzheimer sdisease, rhythmic features are also proposed. For transcription analysis, twosystems are proposed: one uses GloVe word embedding features and the other usesseveral features extracted by language modelling. Several intra-modality andinter-modality score fusion strategies are investigated. The performance ofsingle modality and multimodal systems are presented. The achieved results arepromising, outperforming the results achieved by the ADDReSS s baselinesystems.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×