Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

DeepDyve requires Javascript to function. Please enable Javascript on your browser to continue.

Predicting Prosody from Text for Text-to-Speech Synthesis

Part of the SpringerBriefs in Electrical and Computer Engineering Book Series

DOI: 10.1007/978-1-4614-1338-7

ISBN: 978-1-4614-1337-0

Publisher: Springer New York - Springer Journals

Mar 27, 2012

Available

Introduction

Rao, K. Sreenivasa

Pages: 1 –6

[This chapter discuss about the significance of prosody knowledge for developing speech systems by machine, and for performing various speech tasks by human beings. The manifestation of prosodic knowledge in speech at linguistic, articulatory, acoustic and perception levels is described. Some of...
Available

Prosody Knowledge for Speech Systems: A Review

Rao, K. Sreenivasa

Pages: 7 –25

[This chapter provides an overview of some of the existing models for acquisition of prosody and also methods for incorporating the prosody in speech signal. The models used for capturing the prosody range from rule-based models to data-based models. Rule-based models often generalize too much...
Available

Analysis of Durations of Sound Units

Rao, K. Sreenivasa

Pages: 27 –39

[This chapter presents the detailed analysis of durations of sound units. Durations of the syllables are analyzed with respect to positional and contextual factors. For detailed duration analysis, syllables are categorized into groups based on size of the word and position of the word in the...
Available

Modeling Duration

Rao, K. Sreenivasa

Pages: 41 –63

[This chapter presents modeling of durations of syllables. Features representing linguistic and production constraints are proposed for modeling the durations of syllables. Feedforward Neural Network (FFNN) and Support Vector Machines (SVMs) are proposed for predicting the durations of syllables....
Available

Modeling Intonation

Rao, K. Sreenivasa

Pages: 65 –75

[This chapter discuss about modeling of intonation patterns using feedforward neural networks (FFNN) and Support Vector Machines (SVMs). Linguistic and production constraints are represented in the form of positional, contextual and phonological features for modeling the intonation patterns of...
Available

Prosody Modification

Rao, K. Sreenivasa

Pages: 77 –96

[This chapter focuses on the incorporation of duration and intonation information in a speech signal. A new method is proposed for the modification of pitch and duration of a given speech signal using the instants of significant excitation as anchor points. The method is based on exploiting the...
Available

Practical Aspects of Prosody Modification

Rao, K. Sreenivasa

Pages: 97 –111

[This chapter discuss about the practical aspects of prosody modification. A computationally efficient method for determining the instants of significant excitation is proposed. The application of proposed duration and intonation prediction models has been demonstrated using concatenative text to...
Available

Summary and Conclusions

Rao, K. Sreenivasa

Pages: 113 –116

[This chapter summarizes the research work presented in this book, highlights the contributions of the work and discusses the scope for future work.]

results per page

Prev
1
Next

Browse All eBooks