Text-to-speech System For Afaan Oromoo

A natural way of communication between humans is through speech. On the contrary human machinerncommunication has been limited to keying in instructions and receiving answersrnthrough text forms. This limitation of human-machine communication is now being solved byrnthe development of Dialogue systems. These systems enable human-computer communicationrnvia speech. Besides having natural way of communication.rnOne component of a Dialogue system is a Text-to-speech synthesizer (TTS). It reads textsrnaloud. This component gives opportunities to handicapped people to have access to electronicrndocuments. Moreover it can be used for proofreading documents, language education etc.rnIn this study an attempt is made to address the issue of having textual information in speechrnforms for the language of Araan In doing so a dip hone based text to speech systemrnfor Afaan Oromoo sample words is presented. The present prototype system consists of twornmain parts. These arern• an automatic phonetic transcription of the input word andrn• a speech synths is module which synthesizes an utterance by looping (concatenating)rnthe sound equivalents of the phonetic transcriptionrnTo test the algorithm, samples of words are selected. The selection was based on prevIOUSrnstudy result that showed the most frequent words in some A/aan Or011100 texts.rnDi phones, speech units that cover two sounds and the transition between them, form the basis ..... .rnof the synthesis module. In transcribing the orthography (the writing system) into phoneticrnunits, the Aji:tan Orol11oo writing system is found to be well governed to rules. This enabledrnthe transcription to be accurate. On the contrary, success on recogni zing the utterance of therntran scribed phonetic unit was only li mited to 43.33 % for naive listeners and to 83.33% forrnli steners who heard the utterance at least tlu'ee times in different days.rnError rates of 37 % can be found in some Engli sh Text-to-Speech system. The result of thisrnwork is therefore encouraging and open to reaching higher rates of intelligibility with somernimprovements. Incorporating spectral smoothing techniques that smooth the transition pointsrnof dip hones can make improvements. Moreover, it is felt that having sound laboratory tornrecord the corpus data for such kinds of work is mandatory.

Get Full Work

Report copyright infringement or plagiarism