Predictions from "speech banana" and audiograms: Assessment of hearing deficits in Thai hearing loss patients

"Speech banana" is a banana-shaped plot of speech power distribution, where the abscissa and ordinate represent frequency and intensity. By superimposing speech banana over an audiogram, tested with pure tones, degrees of gain or loss of individual speech sound could be predicted. Speech banana has been constructed for English [1] and Swedish [2]; however, none has been proposed for tonal languages, such as Thai. This work presents a construction of Thai speech banana (TSB), a language with 21 initial consonants and 5 lexical tones. Specifically, intensity of each phoneme in the speech banana was calculated by differences of sound pressure level between the local maxima of power spectral density and 0 phon equal loudness contour. Distribution of the 21 consonants is around 170-5,750 Hz and 10-50 dB. Predictions of gain or loss of the phonemes from the constructed speech banana and audiograms were evaluated based on perception test results from seven Thai sensori-neural hearing loss patients, where they identified what they heard from a pair of 210 rhyming words differing in initial phonemes. Interestingly, the results showed high sensitivity rates of 85.7-100% and high negative predictive values of 50-100%. Specificity rates were at 6.3-33.3% and positive predictive values at 20-44.4%.