Enhancing hearing of computer commands for the aging Chinese population by filtering the initial consonant sounds

Abstract

The objective of this study was to achieve the following goals: identifying the initial consonant sounds in Mandarin Chinese that can be selectively lost by aging people and proposing a filtering method to improve the hearing performance of the aging Chinese population. Past literatures reported that high-frequency hearing loss could produce difficulties for the characters like f, s, t and z in English. It was found in this study that the high-frequency initial consonants in Mandarin Chinese including t, f, s, p, q (as ch in chance), ch (no corresponding pronunciation in English), sh (as sh in sheep) and zh (no corresponding pronunciation in English). Furthermore, a filtering method to enhance the hearing performance of aging Chinese people was proposed which filtered the higher spectral components and boosted the lower spectral components for the older male Chinese, and filtered the lower spectral components and boosted the higher spectral components for the older female Chinese. Thirty participants whose native language is Mandarin Chinese voluntarily took part in the experiment. The result indicated that the above-mentioned eight initial consonants were associated with a higher error rate of speech recognition than the other ones in Chinese. At the same time, the proposed method successfully reduced the error rate of speech recognition, which achieved the goal to improve the speech recognition ability of older Chinese. Relevance for Industry The results of this study will benefit information technology companies that wish to develop software or information services for older Chinese. In addition, by applying the filtering method proposed in this study, the performance of hearing aids is also expected to be improved.