Phonetic-acoustic and feature analyses by a neural network to assess speech quality in patients treated for head and neck cancer

Marieke De Bruijn*, Irma Verdonck-de Leeuw, Louis Ten Bosch, Joop Kuik, Hugo Quené, Lou Boves, Hans Langendijk, René Leemans

*Corresponding author for this work

Research output: Contribution to conferencePaperAcademic


Subjective speech evaluation is the gold standard to assess speech quality of head and neck cancer patients. This study investigates if conventional acoustic-phonetic and novel feature analysis contribute to the development of a multidimensional speech assessment protocol. Speech recordings of 51 patients 6 months post-treatment and of 18 control speakers were subjectively evaluated for intelligibility, nasal resonance and articulation. Self-evaluation of speech problems was assessed by the EORTC QLQ-H&N35 speech subscale. Feature analysis was performed to assess objectively nasality in vowels /a,i,u/. Results revealed that size of the vowel triangle, pressure release of /k/ and nasality in /i/ predict best intelligibility, articulation and nasal resonance and differentiated best between patients and controls. Within patients, /k/ and /x/ differentiated tumour site and tumour classification. Various objective variables were related to speech problems as reported by patients.

Original languageEnglish
Number of pages4
Publication statusPublished - 2008
EventINTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association - Brisbane, QLD, Australia
Duration: 22 Sep 200826 Sep 2008


ConferenceINTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association
CityBrisbane, QLD

Cite this