Data-driven Formant Synthesis of Speaker Age

This paper briefly describes the development of a research tool for analysis of speaker age using data-driven formant synthesis. A prototype system was developed to automatically extract 23 acoustic parameters from the Swedish word ‘själen’ [ˈɧɛːlən] (the soul) spoken by four differently aged female speakers of the same dialect and family, and to generate synthetic copies. Functions for parameter adjustment as well as audio-visual comparison of the natural and synthesised words using waveforms and spectrograms were added to improve the synthesised words. Age-weighted linear parameter interpolation was then used to synthesise a target age anywhere between the ages of 2 source speakers. After an initial evaluation, the system was further improved and extended. A second evaluation indicated that speaker age may be successfully synthesised using data-driven formant synthesis and weighted lienar interpolation.