Strike a balance between theory and practice! With this text, you'll, find a balance between theory and practice that allows you to build your understanding of the basic concepts, assumptions, and limitations of the theory of speech analysis and synthesis. The methods for data analysis as well as the theoretical background are provided to help you comprehend the analysis results. And you'll be able to study the features and properties of speech as a signal without having to record data and write software to analyze the data. The text includes two CDs that contain stand-alone and MATLAB software and speech and electroglottographic data. The CDs illustrate the effects that speech models and speech analysis procedures have on the quality of synthesized speech. An extensive speech database provides numerous speech files and other data. Examples included in each chapter demonstrate how to use the software. The CDs allow you to:
* Calculate the parameters of linear prediction speech models.
* Examine procedures for converting the speech of one speaker to sound like that of another speaker (i.e., voice conversion).
* Analyze and alter the temporal structure of the speech signal. This allows you to automatically parse speech into various features, such as voiced segments, unvoiced segments, nasal and non-nasal segments, fricatives, stops, and more.
* Create speech with a "high speaking rate" or generate speech with a "slow speaking rate."
* Adjust the parameters of the vocal fold model to change the vocal fold tension, length, thickness, mass, etc., in order to observe the effects of these parameters on the vibratory motion of the vocal folds.
* Calculate the parameters of linear prediction speech models.
* Examine procedures for converting the speech of one speaker to sound like that of another speaker (i.e., voice conversion).
* Analyze and alter the temporal structure of the speech signal. This allows you to automatically parse speech into various features, such as voiced segments, unvoiced segments, nasal and non-nasal segments, fricatives, stops, and more.
* Create speech with a "high speaking rate" or generate speech with a "slow speaking rate."
* Adjust the parameters of the vocal fold model to change the vocal fold tension, length, thickness, mass, etc., in order to observe the effects of these parameters on the vibratory motion of the vocal folds.
