Current Trends, Frameworks and Techniques Used in Speech Synthesis – A Survey
Benoy Kumar Thakur1, Bhusan Chettri2, Krishna Bikram Shah3
1Benoy Kumar Thakur, Department of Computer Science and Engineering, Sikkim Manipal Institute of Technology, Majitar, Sikkim, India.
2Bhusan Chettri, Department of Computer Science and Engineering, Sikkim Manipal Institute of Technology, Majitar, Sikkim, India.
3Krishna Bikram Shah, Department of Computer Science and Engineering, Sikkim Manipal Institute of Technology, Majitar, Sikkim, India.
Manuscript received on April 11, 2012. | Revised Manuscript received on April 14, 2012. | Manuscript published on May 05, 2012. | PP: 442-446 | Volume-2 Issue-2, May 2012 . | Retrieval Number: B0645042212/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Vocalized form of human communication is Speech. Here, we have reviewed some of the most popular and effective techniques used to generate synthetics speech. In this quest we are able to find the scenario where one method is advantageous over another. We have discusses Text To Speech Architecture putting more emphasize on the two components, namely, Natural Language Processing (NLP) and Digital Signal Processing (DSP). We have also reviewed some of the most popular generic frameworks like MBROLA, FESTIVAL, and FLITE that available in public domain for the development of a TTS synthesizer.
Keywords: Speech Synthesis, Synthesized Speech, Text-to-Speech, TTS, Artificial Speech, speech synthesizer.