sound

YorubaName Now Has Audio!

I am excited to announce to you today that we have launched a crucial part of the YorubaName vision: audio.

One of the crucial elements planned for this dictionary since its inception has been a voice element. The project itself was conceived in part because of the problem of pronouncing Yorùbá names illustrated in this video of David Oyèlọ́wọ̀ on Jimmy Fallon’s show, a problem believed to be caused only by the absence of a place online where Yorùbá speakers, learners, and foreigners interested in the culture, can go to hear how names are pronounced.

The problem has finally been solved. We have incorporated an audio element into the dictionary. You can now click on the audio icon beside a name and hear how it is pronounced.

Try it out by searching for a name entry you’d like to hear pronounced!

 

A little word on the voice element

As I wrote in a blog post in April 2015, the biggest obstacle to achieving appropriate auto-pronounce was technology. There was no available computer voice in Yorùbá (and as far as we were concerned it had not been created before). So we had a choice of employing one person to pronounce all the names in the dictionary (a very tedious and expensive choice indeed), or creating – through speech synthesis – the technology that can do it automatically for every new addition. The latter option required only the knowledge of the tools necessary, and far less funding than having to bring someone to pronounce each entry in the dictionary.

We didn’t like that limitation and we committed to breaking it. We wanted to create an automatic Yorùbá voice for the dictionary. We also wanted to work towards interesting speech synthesis applications that can enhance African languages in technology.

Read: “What We Are Building Next” on Medium

We achieved the technical breakthrough as far back as 2015, as you would read in the blog post, but never had the funds to get complete the cycle. Hence, earlier this year, we proposed a crowdfunding on indiegogo effort to raise appropriate funds to complete the work.

We raised $1,672.

Through these funds and the generous time of volunteers, the work has now been completed. We no longer need to get one person to record all the names. The software will pronounce as many new names as are added to the dictionary from now on, whether they be 10,000 names or more.

I wrote the phonological rules for the application and provided the voice you now hear. Turning the language rules into software was done by Adédayọ̀ Olúòkun. Getting the work incorporated into the dictionary in a final deployment was done by Dadépọ̀ Adérẹ̀mí. We intend to add a female voice and improve on the output as time goes on.

Through this technology, we have solved one problem and enhanced this dictionary experience. But there are many more ways in which ideas of this nature can (and will) change the world by enhancing the African language experience in technology and on the internet. We hope to be a part of that future.

Hear the names

We hope you enjoy using the dictionary to hear the names pronounced, learning the names of your friends, and becoming more fluent in Yorùbá. Please let us know what you think, especially if some of the names do not render the way you expect them to. We assume that there will be a few glitches here and there and we look forward to fixing them.

On Achieving Auto-Pronounce

One of the thing we wanted this dictionary to have from the very start was a function to allow the user click and hear the audio pronunciation of a name of their choice. This is a standard feature in most online dictionaries. To achieve it, however, posed a very tough problem: how do we get one person to pronounce over tens of thousands of names, correctly, within the time needed for the dictionary to launch. A second problem: how do we get enough money to pay for the data space required to host such a huge body of audio data?

We acknowledged the dilemma: to find a way to host the audio on an affordable space, or to teach the computer to pronounce the names without having to host a human audio at all. A solution, when it came, fell in-between those two choices. It was possible, it turns out, to get a human to pronounce a finite set of audio and tonal segments, and to get the computer use this data to create an infinite number of words, with something that resembles match-making (the technical word is “concatenation”).  It required a knowledge of phonology in the target language, and a grasp of computer permutation procedures. Two of us working on this happened to be competent, individually, in these areas. (I expect Dadépọ̀ to, at some point in the future, write about how the technical aspect came together).

Fullscreen capture 422015 50346 PM.bmp

It took a couple of days pronouncing the test audio, covering hundreds of segments of sound in Yoruba in all their tonal iterations, along with all those vowels matched with all the consonants in the language. Feeding this to a computer program that recognizes how to match these together when presented with a Yoruba word is the next step. As the software department found out during last week of manual matching, it is something that is possible on a grand scale.

The preliminary results from manual matching are here and it blew my mind. Click here for the name “Bádé̩jọ” and here for “Kọ́lá”. Those are auto-pronounced names, half-done by man and half-done by the computer. It was a major breakthrough on which a larger future work can be based, and through which any word in the Yoruba (or any other) language can be realized by a computer through this process of concatenation.

The possibilities now seem limitless although there are still other things to sort out in the coming weeks. As it also turns out, this process (part of something larger, called “speech synthesis”) isn’t new at all, and is credited with a lot of advancement in speech technology all over the world. If we succeed, the we would have shifted a massive obstacle in the way of African language technology.

Next step, get a good professional female voice to do this again. I don’t think that many people expect a male voice while browsing a dictionary 🙂