December 9, 2021 12:00 pm - December 9, 2021 2:00 pm
Asia and the Pacific | India | Bhubaneswar | Veer Birsa Munda Ho Students Union, Odisha
There is a global shift towards using audio-visual media for communications and rightly so. Because an individual with illiteracy or blindness can still hear and understand from an audio recording even though they cannot read. This is exactly why radio as a technology has lived a long life. There is a drastic increase in access to smartphones and mobile data is becoming cheaper. This is good news for any language that has low or limited resources as there is an opportunity to innovate with available technology. If a language has a script and the unique pronunciations of that language can be mapped to the words, it is possible to find a solution for creating a text-to-speech engine. A text-to-speech engine helps read any text in a language that has a script. This benefits a person with illiteracy or blindness or every single user who would like to hear (and not read). However, most low-resource languages do not have enough audio recordings to create a text-to-speech engine. So, creating a decent audio library of all / most words in a language is a starting point.
As a response to the International Decade of Indigenous Languages, many language digital activists are working towards building capacity and resources to promote their own languages. This workshop is for discussing with the Ho youths at the Veer Birsa Munda Ho Students Union, Odisha their plans, the state of audiovisual media in the Ho language, and provide a capacity-building training for creating audio recording of pronunciations of words, a crucial resource for future speech technology development.