论文信息 - Using acoustic models to choose pronunciation variations for synthetic voices

Using acoustic models to choose pronunciation variations for synthetic voices

Within-speaker pronunciation variation is a well-known phenomenon; however, attempting to capture and predict a speaker's choice of pronunciations has been mostly overlooked in the field of speech synthesis. We propose a method to utilize acoustic modeling techniques from speech recognition in order to detect a speaker's choice between full and reduced pronunciations.

Alan W. Black | Christina L. Bennett

[1] Corey Miller. Individuation of postlexical phonology for speech synthesis , 1998, SSW.

[2] Paul Taylor,et al. Automatically clustering similar units for unit selection in speech synthesis , 1997, EUROSPEECH.

[3] Paul Taylor,et al. Festival Speech Synthesis System , 1998 .

[4] Susan Fitt,et al. Representing the environments for phonological processes in an accent-independent lexicon for synthesis of English , 1998, ICSLP.