Ramiz Kastrati
ABSTRACT
The development of the Text-to-Speech (TTS) field is not at the same level in all countries and for all languages. This was obviously conditioned by the differences in speaking and writing in different languages, but also and by the economic justification for research in national terms. Therefore it is evident that the advancement of this field for local languages has not made any significant progress in comparison with the English language. In this context, within this paper is explored the possibility of using the existing TTS converters dedicated for English language [3], for the Albanian language. In particular eSpeak is treated as a compact open source software for speech synthesizer in English, which uses the method of synthesis formant and supports the synthesis of some other words in other languages. The research is focused on two aspects, in determining the understanding of words generated by this system and in determining the feasibility of using eSpeak for generating of speech in Albanian.
- Bickley C, Syrdal A, and Schroeter J. (1998). Speech Synthesis: in the Acoustics of Speech Communication, Picket J. M, Ed., Boston, NY: Allyn and Bacon.Google Scholar
- D. L. Gibson, T. J. Gillott and L. A. Helliker. "Textalk: the BT text to speech system", Br Telecom Techol J 6, No 2,(April 1988.Google Scholar
- D. J. Ravi, Sudarshan Patilkulkarni. "Evaluation of kannada text-to-speech {ktts} system", International Journal of Advanced Research in Computer Science and Software Engineering, Volume 2, Issue 1, January 2012Google Scholar
- eSpeak, Available: http://espeak.sourceforge.net/index.html, Accessed: 20.04.2013Google Scholar
- Formant Synthesis, Available: http://www.text2speech.com/formant.html, Accessed: 20.04.2013Google Scholar
- Goldstein M. (1995). "Classification of Methods Used for Assessment of Text-to-Speech Systems According to the Demands Placed on the Listener", Speech Communication vol. 16: 225--244. Google ScholarDigital Library
- IPA, The international Phonetic Association, Available: http://www.langsci.ucl.ac.uk/ipa/fullchart.html Ac-cessed: 19.12.2012Google Scholar
- Lemmetty S. "Review of Speech Synthesis Technology", MSc. Thesis, Laboratory of Acoustics and Audio Signal Processing, Helsinki University of Technology, Finland, 1999.Google Scholar
- Salza, P. L., Foti, E., Nebbia, L., and Oreglia, M. (1996). "MOS and pair comparison combined methods for quality evaluation of text to speech systems", Acta Acustica, 82, 650--656.Google Scholar
- Shaban Demiraj. "The Origin of the Albanians", Academy of Sciences of Albania, Tirana, 1988.Google Scholar
- Shradha Mohanan, Sonam Salkar, al. "Text To Speech Synthesizer for Konkani Language", International Conference on Computing and Control Engineering (ICCCE 2012), 12 & 13 April, 2012Google Scholar
Index Terms
- The opportunity of using eSpeak as text-to-speech synthesizer for Albanian language
Recommendations
Electronic Dictionaries and Transducers for Automatic Processing of the Albanian Language
NLDB '07: Proceedings of the 12th international conference on Applications of Natural Language to Information Systems: Natural Language Processing and Information SystemsWe intend on developing electronic dictionaries and Finite State Transducers for the automatic processing of the Albanian Language. We describe some peculiarities of this language and we explain how FST and generally speaking NooJ's graphs enable to ...
Building an annotated corpus for the Albanian language using bilingual projections and regular expressions
We present research done on creating an annotated corpus for the Albanian language. This corpus is achieved combining unsupervised part-of-speech tagging using bilingual projections with regular expressions. Albanian-English text from a free parallel ...
Robust Arabic speech recognition in noisy environments using prosodic features and formant
This paper investigates the contribution of formants and prosodic features such as pitch and energy in Arabic speech recognition under real-life conditions. Our speech recognition system based on Hidden Markov Models (HMMs) is implemented using the HTK ...
Comments