April 2015

A “Thank You” to Collaborators

One of the things that have lubricated the wheel of this project is the support and hard work of a number of people working on different parts on the project, all without pay, and mostly without any glory. Like the ancient translators, many of whom are not even recorded in history, but who dutifully dedicated their time and energy to translating the bible and English hymns into Yoruba and a number of all African languages, there are people on this project without whom we wouldn’t have achieved anything, but with whose dedication I can say confidently that the next couple of weeks will be an exciting one for this dictionary project.

I also want to use this blog post to especially thank the folks at Capital Square, a co-working space in Lagos with whose collaboration we can now use a dedicated “studio” space somewhere in Lekki to record the audio data needed for the TTS (text-to-speech) functionality of the dictionary. I spent some time this weekend in the conducive embrace of that working space, creating a new set of relevant audio recordings. For those who remember, it was on the blog of that same organisation where a guest post I wrote about the dictionary project, while fundraising was still ongoing, was first published.

And while the work continues, here’s a toast to all those whose energy and zeal make it all possible, including a few new volunteers on our dictionary project. Thank you, everyone.

From language learner to active volunteer

lailaIt’s odd that I found myself volunteering with Yoruba Names and at the same time it’s the most natural thing in the world.

Like Vanessa in the novel In Dependance by Sarah Ladipo-Manyika, there was a time I used to ask myself “Do your names really mean what you say they do?” (…) “Or is this how you like to charm the girls?”. Now that I’ve started learning Yorùbá, I may not be quite as clueless but that sense of wonder has not abated, for I’ve been fortunate enough to come across the most inspiring teachers both at school and online.

My involvement in this project stems from a growing conviction that the diversity of languages existing in the world needs to be better represented online and that we can all take a part in making this happen. On a more personal level, it’s a source of great enjoyment both to learn more about Yorùbá names along the way, and to do so in the company of other passionate volunteers from various backgrounds.

I am going to be the Bénin connection in the team, working in collaboration with Yorùbá speakers as well as local scholars to document the names found in the country. Apart from preparing for this upcoming field work, I am active on the social media and copy-editing fronts, making sure that the world knows what’s happening with the Yoruba Names Dictionary!

Of course, I’m not so naive as to expect everyone to instantly start caring about the accurate pronunciation of names, and even less so about their meaning and history, but it will be quite an achievement if one day soon, the information is available for anyone to look up on their laptops, phones, tablets, or whichever device will have been invented in the years to come.

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 🙂

Yoruba Names Do Not Have To Trip Many

If you come by a Yoruba name and perchance you happen not to be familiar with the Yoruba culture and language, their is the chance you would probably trip trying to get the name’s pronunciation right: not to talk about understanding and appreciating the name’s meaning and what it represents. This should not have to be the case; you do not have to trip over Yoruba names: and even if you do the first time, you should be able to have access to tools/resources that teaches you and helps you get it right the second time.

Here in an article in New York times press which exemplify exactly how Yoruba names might be a daunting one to decipher, but it also illustrates precisely some of the problems we’re going to be solving with the dictionary. The Yoruba name dictionary would end up being a place where Yoruba names can be appreciated, their meaning understood and their right pronunciation learnt.

Do have a nice time reading the article, and keep your fingers crossed as we count down to launch!