An HMM-based speech synthesis framework is applied to both Standard Austrian German and a Viennese dialectal variety and several training strategies for multi-dialect modeling such as dialect clustering and dialect-adaptive training are investigated. For bridging the gap between processing on the level of HMMs and on the linguistic level, we add phonological transformations to the HMM interpola...

a total of 698 blood and serum specimens from residents of 13 iranian communities were examined by plaque reduction neutralization test for antibodies to west nile virus. in general, infection rates in the north of the country were low while higher rates were observed among residents of central and southwestern iran. the highest prevalence of infection was found among residents of khuzestan pro...

In this paper, we show how adaptive modeling within the statistical parametric speech synthesis framework can be applied to Albanian dialects. We develop speaker dependent voices for the Tosk and Gheg dialect and adapt models for the Gheg dialect from the Tosk models. We show that the adapted Gheg models outperform the speaker dependent Gheg model on an intelligibility and dialect classificatio...

Dialect loss is a relatively new but by now quite general phenomenon in Flanders (i.e., Dutch-speaking Belgium). Although the processes of dialect change and dialect loss have proceeded with great regional di¤erences in speed and intensity in the past decades, there is a general tendency toward replacing primary dialect features of a relatively local scope by secondary dialect features that hav...

22 Moving from a traditional dialect geography research methodology to one in which data are processed 23 electronically and where visualization is used as a research tool can be of great benefit to dialect geography. 24 A working environment offering full support for using visualization as a research tool could take dialect 25 geography into the era of eScience. Despite the advent of electroni...

This paper describes a method for selecting an appropriate phone set in dialect speech synthesis for a so far undescribed dialect by applying hidden Markov model (HMM) based training and clustering methods. In this pilot study we show how a phone set derived from the phonetic surface can be optimized given a small amount of dialect speech training data.

The purpose of this article is to determine the phonemic status of [h] and [ʔ] in the Sistani dialect of Miyankangi. Auditory tests applied to the relevant data show that [ʔ] occurs mainly in word-initial position, where it stands in free variation with Ø. The only place where [h] is heard is in Arabic and Persian loanwords, and only in the pronunciation of some speakers who are educated and/or...