Prosodic Modeling For Amharic

During daily speech communications, we systematically employ variations in pitch,rnloudness, phrasing and duration of spoken segments to express our intentions, attitudesrnand assumptions. These cues are continuously picked by our listeners and our intentionsrnare communicated. This phenomenon is what is termed as prosody. Various languagesrnhave been modeled using a prosodic modeling framework and have been used to varyingrndegrees of success in applications like speech synthesis systems. The prosodic featuresrnof speech are largely dependent on the language, thus it is imperative that prosodicrnmodels be developed and tested for each language to apply them in (language specific)rnspeech synthesis applications. In this study the prosodic nature of Amharic isrninvestigated, and based on the investigation the prosodic cues of Amharic are identifiedrnand an Amharic prosodic model based on the ToBI framework is developed. Thisrnhypothesized model is then be subjected to a rigorous test to determine whether it resultsrnin improvement of Amharic synthetic speech in terms of naturalness and intelligibility.

Get Full Work

Report copyright infringement or plagiarism