Human language carries a lot of information. It can be thought of as comprising two channels – the words themselves and style in which they are spoken. The speaking style reflects the state of a person in a particular environment. And the style in which these words are spoken reflects the prosodic information in them. Prosody is a collection of factors that control the pitch, duration and intensity of a speech signal. These prosodic parameters can be controlled in domains like frequency domain and time domain. In this paper we will explore how prosodic information can be controlled and thus the speech can be modified in time domain.

1. Hoult, C. May 2004. Emotion in speech synthesis.
2. Chandak, M. B. , Dharaskar, R. V. and Thakre, V. M. 2010. Text to Speech Synthesis with Prosody feature: Implementation of Emotion in Speech Output using Forward Parsing. In the Proceedings of International Journal of Computer Science and Security.
3. Thakur, S. K. , Satao, K. J. 2011. Study of various kinds of Speech Synthesizer Technologies and Expressions For Expressive Text To Speech Conversion System. In the Proceedings of International Journal of Advanced Engineering Sciences and Technologies.
4. Ishpreet Kaur, Manveen Kaur Oberoi, Simrat Kaur. 1-2 Nov 2012. A Survey on Approaches to Emotional Speech Synthesis and Parameters to control Emotions. In the Proceedings of Speech, Image, Biomedical and Information Processing 2012 (SIBIP 2012), International Conference at Chitkara University, Nov2012.

Prosody Prosody Modification Time-domain