ABSTRACT
Being necessary for a Text-To-Speech (TTS) system, text-normalization is general a challenging problem, especially for Vietnamese because of the local context. Recent researches in text-normalization in Vietnamese for TTS systems are still at the beginning with very simple sets of ad hoc rules for individual cases in spite of the ambiguity of real text. The purpose of this paper is to take some initial steps towards methodically normalizing input text in Vietnamese for a TTS system. This paper proposes a categorization and a normalization model for Vietnamese text based on related results for other languages. An experimental application is implemented to demonstrate the model, which uses several techniques including letter language model and decision trees for classifying NSWs and both supervised and unsupervised approaches for expanding abbreviations.
- Taylor Paul. Text-To-Speech Synthesis. s.l.: Cambridge University Press, 2009.Google Scholar
- Xuedong Huang, Alex Acero and Hsiao-wuen Hon. Spoken Language Processing, A guide to Theory, Algorithm, and System Development. s.l.: Prentice Hall, 2001. Google ScholarDigital Library
- Richard Sproat, Alan Black, Stanley Chen, Shankar Kumar, Mari Osten-dorf, and Christopher Richards. Normalization of Non-StandardWords. Computer Speech and Language, Volume 15, Issue 3. July 2001, pp. 287--333.Google ScholarDigital Library
- Hindi Text Normalization. K. Panchapagesan, Partha Pratim Talukdar, N. Sridhar Krishna, Kalika Bali, and A. G. Ramakrishnan. Hyderabad, India: s.n., 19--22 December 2004. Fifth International Conference on Knowledge Based Computer Systems (KBCS).Google Scholar
- Non-Standard Word and Homograph Resolution for Asian Language Text Analysis. Craig Olinsky, and Alan W Black. Beijing, China: s.n., 2000. Sixth International Conference on Spoken Language Processing (ICSLP 2000).Google Scholar
- Text Normalization for the Pronunciation of Non-Standard Words in an Inflected Language. Gerasimos Xydas, Georgios Karberis, and Georgios Kouroupertroglou. Samos, Greece: s.n., May 5--8, 2004. 3rd Hellenic Conference on Artificial Intelligence (SETN04).Google Scholar
- Text Normalization System for Bangla. Firoj Alam, S. M. Murtoza Habib, and Mumit Khan. Lahore, Pakistan: s.n., January 22--24, 2009. Conference on Language and Technology 2009 (CLT09).Google Scholar
- Text Processing for Text to Speech Systems in Indian Languages. Anand Arokia Raj, Tanuja Sarkar, Satish Chandra Pammi, Santhosh Yuvaraj, Mohit Bansal, Kishore Prahallad, and Alan W Black Bonn, Germany: s.n., 2007. 6th ISCA Speech Synthesis Workshop SSW6.Google Scholar
- Sao Mai Computer Center for the Blind. Sao Mai Voice. Trung tâm Tin học Vì ngu'òi mù Sao mai (Sao Mai Computer Center for the Blind - SMCC). {Online} http://www.saomaicenter.org/category/general-category/bộ-đọc-sao-mai.Google Scholar
- International Research Center MICA. Hoa Sung. {Online} http://www.mica.edu.vn/tts.Google Scholar
- Speech Language Processing Group, HCMUS. Tiếng nói Phuo'ng Nam (Voice of Southern Vietnam - VOS). AILAB Laboratory, University of Science Ho Chi Minh city, Vietnam {Online} http://www.ailab.hcmus.edu.vn/slp/vos/default.aspx.Google Scholar
- Statistical Methods for Speech Recognition. s.l.: MIT Press, Cambridge, 1997. Google ScholarDigital Library
- Induction of decision trees. J. Ross Quinlan. 1986, Machine Learning 1, Vol. 1, pp. 81--106. Google ScholarDigital Library
- Simplifying Decision Trees. J. Ross Quinlan. 1987, International Journal of Man-Machine Studies 27, Vol. 3, pp. 221--234. Google ScholarDigital Library
- Đoàn Thiện Thuật. Ngữ âm tiếng Việt. s.l. : NXB Đại học Quốc gia Hà Nội (Vietname National University Publisher), 1997.Google Scholar
- Trần Ngọc Dụng. Cẩm Nang Ngữ Pháp Tiếng Việt (Vietamese Grammar Handbook). {Online} 2009. tinhhoavietnam.net.Google Scholar
- Mai Ngọc Chừ, Vũ Đức Nghiệu, and Hoàng Trọng Phiến. Cơ sở ngôn ngữ học và tiếng Việt (Education Publication), 2000.Google Scholar
- Ngôn ngữ học và tiếng Việt (Linguistics, Vietnamese and more...). {Online} http://ngonngu.net.Google Scholar
- Improved backing-off for n-gram language modeling. Kneser, Reinhard and Hermann Ney. 1995. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Vol. 1, pp. 181--184.Google Scholar
- Bell, T. C., J. G. Cleary and I. Witten. Text Compression. s.l.: Prentice Hall, Englewood Cliffs, 1990. Google ScholarDigital Library
Recommendations
Multi-task Text Normalization Approach for Speech Synthesis
PRICAI 2021: Trends in Artificial IntelligenceAbstractText normalization for Text-To-Speech includes several challenging tasks in natural language processing such as verbalizing abbreviations, Out-Of-Vocabulary (OOV) words, and chunking phrases for long sentences without punctuation. Instead of ...
An Experimental Study on Vietnamese Speech Synthesis
IALP '11: Proceedings of the 2011 International Conference on Asian Language ProcessingThe modern Vietnamese is a monosyllabic tone language. Each syllable can be marked with initial, final and tone. In this paper, Vietnamese speech synthesis system is realized by using a trainable HMM-based speech synthesis method. The basic synthesis ...
Learning Vietnamese-English Code-Switching Speech Synthesis Model Under Limited Code-Switched Data Scenario
PRICAI 2021: Trends in Artificial IntelligenceAbstractRecent advances in deep learning facilitate the development of end-to-end Vietnamese text-to-speech (TTS) systems that produce Vietnamese voices with high intelligibility and naturalness. However, enabling these systems to speak Vietnamese and ...
Comments