Please I need a support and ideas on how to carry out a project/research on Automatic Speech Recognition (ASR) for Yorùbá language. Many works have been done on ASR but none (to the best of my knowledge) has been carried out on Yorùbá language. Yorùbá language is a tonal language in which words of the same phonemes can have different meanings, e.g. igbá - "calabash" , igba - "200", ìgbà - "period", ìgbá - "garden egg", igbà - "climbing rope". This makes the recognition difficult.
Please, if you know of any solution, you can kindly reply here or mail me: mfayemiwo@gmail.com
Your contributions will be highly appreciated.

Kudos to you on the project and I wish you Gods speed.

milkytins:
Please I need a support and ideas on how to carry out a project/research on Automatic Speech Recognition (ASR) for Yorùbá language. Many works have been done on ASR but none (to the best of my knowledge) has been carried out on Yorùbá language. Yorùbá language is a tonal language in which words of the same phonemes can have different meanings, e.g. igbá - "calabash" , igba - "200", ìgbà - "period", ìgbá - "garden egg", igbà - "climbing rope". This makes the recognition difficult.
Please, if you know of any solution, you can kindly reply here or mail me: mfayemiwo@gmail.com
Your contributions will be highly appreciated.

Well..I don't think it is too difficult, no speec recognition is 100 percent accurate, more training of your voice makes the program better understand you and for the issue you raised, it is not so difficult to implement.

Check my signature for my whatsapp or BBM, let's chat real time

Well, trust me. The best way to go about it is by using machine learning. Let the computer learn the difference on its own. Support vector machines, artificial neural networks and deep neural networks should be sufficient