Deriving disyllabic word variants from a Chinese conversational speech corpus
Journal
Journal of the Acoustical Society of America
Journal Volume
140
Journal Issue
1
Pages
308 - 321
Date Issued
2016
Author(s)
Abstract
Motivated by the quasi-categorical reduced forms of disyllabic words produced in Chinese conversational speech, a frequency-based selection procedure of typical pronunciation by disyllabic word type and reduction degree is proposed in this paper. This variant-selection algorithm utilizes techniques of free phone recognition and phonetic similarity score calculation to account for Chinese syllable structure. Four reduction types are suggested by considering the presence of a within-word syllable boundary: Citation form-like reduction, marginal segment deletion, nuclei merger, and syllable merger. The results show that the most frequent reduction types for disyllabic words in Chinese conversation are citation form-like reduction and syllable merger. In particular, high-frequency disyllabic words preferentially take the extreme syllable-merger form. As shown in the analysis, segmental reduction in Chinese disyllabic words is morphology-dependent. It is also related to the prosodic position at which a disyllabic word is produced as well as the temporal quality of the word. Finally, in the automatic speech recognition experiments, the performance was improved by adding a small number of variants selected by the algorithm to the pronunciation dictionary of the system. © 2016 Acoustical Society of America.
SDGs
Other Subjects
Mergers and acquisitions; Merging; Automatic speech recognition; Conversational speech; Frequency-based selection; High frequency HF; Pronunciation dictionaries; Similarity scores; Syllable boundaries; Syllable structures; Speech recognition; algorithm; China; human; phonetics; physiology; speech; speech analysis; speech perception; Algorithms; China; Humans; Phonetics; Speech; Speech Articulation Tests; Speech Perception
Type
journal article