Artificial neural network analysis to assess hypernasality in patients treated for oral or oropharyngeal cancer

Marieke de Bruijn, Louis ten Bosch, Dirk J. Kuik, Johannes A. Langendijk, C. Rene Leemans, Irma Verdonck-de Leeuw*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

9 Citations (Scopus)

Abstract

Objective. Investigation of applicability of neural network feature analysis of nasalance in speech to assess hypernasality in speech of patients treated for oral or oropharyngeal cancer. Patients and methods. Speech recordings of 51 patients and of 18 control speakers were evaluated regarding hypernasality, articulation, intelligibility, and patient-reported speech outcome. Feature analysis of nasalance was performed on /a/, /i/, and /u/ and on the entire stretch of speech. Results. Nasalance distinguished significantly between patients and controls. Nasalance in /a/ and /i/ predicted best intelligibility, nasalance in /a/ predicted best articulation, and nasalance in /i/ and /u/ predicted best hypernasality. Conclusion. Feature analysis of nasalance in oral or oropharyngeal cancer patients is feasible; prediction of subjective parameters varies between moderate and poor.

Original languageEnglish
Pages (from-to)168-174
Number of pages7
JournalLogopedics phoniatrics vocology
Volume36
Issue number4
DOIs
Publication statusPublished - Dec-2011

Keywords

  • Articulation
  • artificial neural network
  • feature analysis
  • head and neck cancer
  • hypernasality
  • objective speech rating
  • oral cancer
  • reconstructive surgery
  • speech quality
  • vowels
  • AUTOMATIC SPEECH RECOGNITION
  • QUALITY-OF-LIFE
  • OVERLAPPING ARTICULATORY FEATURES
  • TRACHEOESOPHAGEAL SPEECH
  • LONGITUDINAL ASSESSMENT
  • EUROPEAN-ORGANIZATION
  • PERCEPTUAL EVALUATION
  • MAXILLECTOMY PATIENTS
  • MICROVASCULAR FLAP
  • SURGICAL-TREATMENT

Cite this