Special Speech Synthesis for Social Network Websites

A survey of diacritic restoration in abjad and alphabet writing systems

“…Spriet and El-Bèze (1997) used a dictionary to determine possible diacritic forms for a given diacritized form. Truyen et al (2008) similarly used only a dictionary of words to generate proposal set for each term, while Zainkó et al (2010) employed a dictionary for deterministically restoring diacritics to forms that have only one diacritical form. Ungurean et al (2008) developed a diacritization model for Romanian based on a set of cascaded filters.…”

“…The difference between the model utilizing this decision list and the Bayesian classifier is that instead of combining all the evidences together it uses the only most applicable and best evidence. Zainkó et al (2010) similarly used decision list for diacritization of words with multiple diacritical forms in Hungarian by modeling at letter level with an expanded context of ten letter to left and right of ambiguous letter within the word. The decision list was supplemented by a dictionary that dealt with words with single diacritical form.…”

“…According to Simard (1998), unaccented French texts were ‘quite common in electronic media, as a result of a long history of character encoding problems and the lack of well-established conventions for typing accented characters on computer keyboards’. The current adhesion to orthographic rule means that absence of diacritics is found mostly on e-mail and short message service messages, social media text and the like (Simard and Deslauriers 2001; Ungurean et al 2008; Zainkó, Csapó and Németh 2010). On the other hand, most Yorùbá textual documents, except for educational textbooks, are written with no or minimal diacritics in the text (Ọdẹjọbí 2005; Adegbola and Odilinye 2012).…”

“…The above situations present a serious challenge to processing by machine, for searching, retrieval, summarization, translation, text-to-speech, spell-checking and grammar-correction among others (Elshafei et al 2006a; Al Badrashiny 2009; Ahmed, Nürnberger and Nitsche 2011; Adegbola and Odilinye 2012) and chat-to-speech (Zainkó et al 2010). Several approaches have been applied to the task of restoring diacritics to text whenever they are absent whether by writing practice or transmission distortion or by limitation of input method.…”