Importance of glottis landmarks for the assessment of cleft lip and palate speech intelligibility

Abstract

The present work explores the acoustic characteristics of articulatory deviations near g(lottis) landmarks to derive the correlates of cleft lip and palate speech intelligibility. The speech region around the g landmark is used to compute two different acoustic features, namely, two-dimensional discrete cosine transform based joint spectro-temporal features, and Mel-frequency cepstral coefficients. Sentence-specific acoustic models are built using these features extracted from the normal speakers' group. The mean log-likelihood score for each test utterance is computed and tested as the acoustic correlates of intelligibility. Derived intelligibility measure shows significant correlation (ρ = 0.78, p < 0.001) with the perceptual ratings.

Subjective and Objective Evaluation of Speech in Adult Patients with Unrepaired Cleft Palate

“…In this study, acoustic spectrum analysis was used as an objective evaluation method for cleft palate speech. The most significant vowel defect in cleft palate patients is excessive nasalization, which is mainly caused by the abnormality of the sound cavity structure caused by the palate cleft, 33,34 long-term studies by linguists have shown that people with cleft palate also have abnormal tongue position and lip shape. 35,36…”

“…In this study, acoustic spectrum analysis was used as an objective evaluation method for cleft palate speech. The most significant vowel defect in cleft palate patients is excessive nasalization, which is mainly caused by the abnormality of the sound cavity structure caused by the palate cleft, 33,34 long-term studies by linguists have shown that people with cleft palate also have abnormal tongue position and lip shape. 35,36 In this study, the first 3 formants of the vowels /a/ and /u/ were not different between the 2 groups of subjects, whereas the F2 and F3 of vowels /i/ in adult cleft palate patients were significantly lower than those in normal adults.…”

Landmark-based analysis of speech differentiates conversational from clear speech in speakers with muscle tension dysphonia

“…LMBAS has been applied to describe acoustic differences associated with dysphonia (Ishikawa, Rao, MacAuslan & Boyce, 2020), speech production disorders in children (Atkins, Boyce, MacAuslan, & Silbert, 2019; Liu 2021; Kalita, Mahadeva Prasanna, & Dandapat, 2018), and depression (Huang, Epps, & Joachim, 2019). A few studies have reported the feasibility of detecting the difference between conversational and clear speech with LMBAS in healthy speakers (Boyce, Bradlow, & MacAuslan, 2005; Boyce, Krause, Hamilton, Smiljanic, & Bradrow, 2013).…”