Proposal of structure-to-speech conversion and its application to implementation of infants’ vocal imitation

Speech acoustics vary due to differences in age, gender, vocal tract length, microphone, and so on. The authors recently proposed a structural and abstract representation of speech, where these variations were effectively removed. This representation captures only dynamics of speech. In our previous study, using this abstract representation, a new framework of speech synthesis was proposed and some fundamental investigations were carried out. In this new framework, an utterance is modeled by two separate attributes; one corresponding to what is known as speech Gestalt, which is speaker-invariant, and the other to the embodiment seen in vocal tubes, which characterizes speaker differences. Acoustic signals are generated by using the Gestalt as constraint conditions and the vocal tube embodiment as initial conditions. In other words, the Gestalt can be acoustically realized only when the speaker’s embodiment is considered. This new framework can be regarded as an implementation of infants’ vocal imitation. In this study, by following the initial investigations, we improve accuracy and efficiency in acoustic realization of the Gestalt by using an analytical method. Experiments of generating continuous utterances of Japanese vowels show the validity of the proposed method.