A LEXICON SET AND SOFTWARE FRAMEWORK FOR TURKISH TEXT-TO-SPEECH SYNTHESIS APPLICATIONS

---

Yilmaz A. E.

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, cilt.24, sa.4, ss.735-744, 2009 (SCI-Expanded, Scopus, TRDizin)

• Yayın Türü: Makale / Tam Makale
• Cilt numarası: 24 Sayı: 4
• Basım Tarihi: 2009
• Dergi Adı: JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY
• Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, TR DİZİN (ULAKBİM)
• Sayfa Sayıları: ss.735-744
• Ankara Üniversitesi Adresli: Evet

Özet

In this work a lexicon set and software framework, which will provide an infrastructure for Turkish text-to-speech synthesis applications, are introduced. The infrastructure consists of functions developed at Microsoft. NET 2.0 environment and XML based rule scripts. The infrastructure functions perform operations such as the correct phonetic representation of a given text; the conversions of acronyms and abbreviations or numerical values inside a text to appropriate written form for correct speech synthesis, etc. In scope of this study, a proprietary phonetic representation has also been defined, and it is described in details in this paper. It is aimed that the infrastructure will provide standardization for the future text-to-speech applications.