Enriching text with tone marks: An application to Kinyarwanda language
نویسنده
چکیده
The absence of tone marks in text can be considered an instance of defective writing. Yet most writing systems of tone languages in Africa do not mark tone. This adds to ambiguity, which must be resolved on the basis of the context. Using tone-marked lexicons and tone rules the ambiguity can be resolved. This paper deals with a further problem, i.e. how to insert tone marks into a text without tone marking. Such a tool is needed in text-to-speech applications, and whenever a text needs to be provided with tone marks. Three approaches are briefly discussed, and one of them is selected for discussion, implementation and demonstration. The implementation makes use of Finite State Methods in analysis, Constraint Grammar in disambiguation, and regular expressions in writing tone rules. The system was implemented using Kinyarwanda verb morphology for testing and demonstration. It is assumed that the approach is suitable especially for tone languages that have lexical and grammatical tone.
منابع مشابه
Quantifying the effect of corpus size on the quality of automatic diacritization of Yorùbá texts
Yorùbá being a tone language requires tone information for the correct pronunciation of words in Text-to-Speech synthesis. Based on standard Yorùbá orthography, such information is held in tone marks, which applied to vowels and syllabic nasals as diacritical markings. However, the tone marks are not always correctly applied in many Yorùbá documents because appropriate input devices for the acc...
متن کاملWhen Marking Tone Reduces Fluency: An Orthography Experiment in Cameroon
Should an alphabetic orthography for a tone language include tone marks? Opinion and practice are divided along three lines: zero marking, phonemic marking and various reduced marking schemes. This paper examines the success of phonemic tone marking for Dschang, a Grassfields Bantu language which uses tone to distinguish lexical items and some grammatical constructions. Participants with a vari...
متن کاملAn African Solution for an African Problem: A step towards perfection
This article reports on a study that involves improving a tone label prediction algorithm. Tone is an important prosodic feature for Bantu languages since these languages use it to distinguish meaning. Studies have shown that text-to-speech systems need detailed prosodic models of a language in order to sound natural to native speakers of the language. Thus, textto-speech systems developed for ...
متن کاملText-dependent speaker identification using neural network on distinctive Thai tone marks
This paper presents a neural network based text-dependent speaker identification system for Thai language. Linear Prediction Coefficients (LPC) are extracted from speech signal and formed feature vectors. These features are fed into multilayer perceptron (MLP) neural network with backpropagation learning algorithm for training and identification processes. Five Thai tone marks are considered ve...
متن کاملComputational Analysis of Kinyarwanda Morphology: The Morphological Alternations
For more than 30 years, there have been renewed interests in computational morphology resulting in numerous morphological tools. However the interest has always been on the politically and economically interesting languages of the world resulting in a wide language divide between the technologically rich and poor languages. Kinyarwanda language, a Bantu language spoken in East Africa is one of ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009