=Paper=
{{Paper
|id=Vol-1755/1-5
|storemode=property
|title=YorCALL: Improving and Sustaining Yoruba Language through a Practical Iterative Learning Approach
|pdfUrl=https://ceur-ws.org/Vol-1755/1-5.pdf
|volume=Vol-1755
|authors=Zainab Abdulkareem,Emmanuel E. Effiong
|dblpUrl=https://dblp.org/rec/conf/cori/AbdulkareemE16
}}
==YorCALL: Improving and Sustaining Yoruba Language through a Practical Iterative Learning Approach==
https://ceur-ws.org/Vol-1755/1-5.pdf
YorCALL: Improving and sustaining Yoruba Language
through a practical Iterative learning Approach
Zainab O. Abdulkareem Efiong E. Edet
Alhikmah University, Ilorin University of Ibadan
abdulkareemzainab01@gmail.com edet_e_emmannuel@yahoo.com
ABSTRACT Indigenous languages as Children's first language and making
The number of people who speak Yoruba language fluently and Indigenous languages a compulsory course to be taken by students
write it correctly with appropriate tonal signs is declining. This in all level of education. However, there is need for more efforts
could be attributed to the adoption of English Language (a that will adopt practical approach to ensure that the language
colonial language) by parent as their children first language and remains intact. To this end, Computer Assisted Language
the neglect of Yoruba from most Nigeria Educational system Learning (CALL) for Yoruba is developed in this project to help
curricula. To this end, the aim of this work was to improve user speakers of Yoruba language to speak correctly and fluently by
knowledge of tonal sign assigning, correct word pronunciation and applying the appropriate tone on words they pronounce.
thus Yoruba language literacy by implementing a Computer CALL is perceived as an approach to language teaching and
Assisted Language Learning System that translates Yoruba text to learning in which the computer is used as an aid to the
speech, and allows users to check-up the meaning of words and presentation, reinforcement and assessment of material to be
take test on Yoruba language literacy. We propose a practical learned, usually including a substantial interactive element [4].
iterative learning approach that factors in the basic features and The computer is used to ameliorate users' knowledge of particular
requirements that will ensure the optimal realization of benefits of Language/languages. CALL has being continually adopted as
the system to the user. medium of learning new languages or improving on old ones.
Over the years CALL is used to incite language learners, provide
CCS Concepts comfortable access to learning material, testing of users
• Computing methodologies ➝Artificial intelligence ➝Natural acquisition level and examining the relevance of call to Learning
language processing ➝Machine translation and Disseminating System (Checking if it has accomplish its
functions and purpose).
Keywords The CALL system provided information which is expected to be
Tonal, Speech, Dataset, Iterative, Translate
responded to by system users. The system in turn process input
and gives appropriate justification of input structure and meaning.
1. INTRODUCTION To improve Flexibility of Computer Assisted Language Learning
Yoruba tribe makes up about 35 million people in total with Interaction between system and users have being adopted, text,
majority constituent from Nigeria (about 21% of Nigeria's static and moving images and audio are used for interactive
population), 1.2 million in Benin, 0.4 million in Ghana, 0.1 Computer Assisted Learning Language System Environment.
million in Togo )0.1 million in Ivory Coast, 0.2 million in Europe
and 0.2 million in North America [15]. Yoruba language is a tonal
By adopting a practical iterative learning approach, this work
language consisting of seven vowel sounds exclusive of nasal
focuses on improving user knowledge of Yoruba tonal sign
vowels and eighteen consonant sounds, making up 25 alphabets
assigning, correct word pronunciation. It also improves Yoruba
and 3 tonal signs (three level tones: high, low and mid (the default
language literacy by implementing a Computer Assisted Language
tone) to distinguish between words with the same spelling but
Learning System that translates Yoruba text to speech, and allows
different pronunciation and meaning. Every Yoruba syllable must
users to check-up the meaning of words and undertake test on
have at least one tone.
Yoruba language literacy.
There is a continued decline in the number of "Yorubas" that can
speak Yoruba language fluently and write it correctly with
appropriate tonal signs. This is as a result of adoption of English 2. BACKGROUND
Language (a colonial language) by parent as their children first Previous studies have focused on CALL by identifying three
language and the neglect of Yoruba from most Nigeria historical phases of CALL and classified them according to
Educational system curricula. underlying pedagogical and methodological approaches [10]. The
To prevent extinction of Nigeria's indigenous languages there have participation of the potential users of the system in CALL
being persistent calls by various esteemed scholars and development cannot be sidelined, which is "the active involvement
organisation to revive Nigeria indigenous languages, by adopting of end-users, as non professional developers, in a software
development life cycle[5]. The contribution of language learners
tutoring system improves the effectiveness of the system design.
The CALL system developers should be focused on getting right
requirements and intelligibly transforming it to a standardised
CoRI’16, Sept 7–9, 2016, Ibadan, Nigeria. design.
2.1 RELATED WORKS
An Intelligent CALL System for Arabic Learners was designed for
Primary Schools and Arabic language learners. The system
1
employed Natural Language Processing for learning the language 2.2 Yoruba Phonemics
and provides learning materials for the users, on which they are Yoruba language is a tonal language consisting of seven oral
expected to take test on. The instructor is able to stipulate vowel sounds, five nasal vowels and eighteen consonant sounds
conditions to determine the test questions specialisation. The and 3 tonal signs (three level tones: high, low and mid (the default
response given by users is analysed using morphological analyser, tone) to distinguish between words with the same spelling but
syntax analyser and semantic analyser. The morphological different pronunciation and meaning. Every Yoruba syllable must
analyser breaks down response of the users to smallest component have at least one tone.
of the language. The syntax analyser checks for the structural
correctness of user's response and form syntactic categories. The Consonant Sounds
Semantic analyser checks for rule based approach to generate b, d, f, g, gb, j, k, l, m, n, p, r, s, ṣ, t, u, w, y
appropriate response to result given by the system users to
promote effective learning. [8] Vowel Sounds
RU_CALL, a standalone system is aimed to provide electronic Oral vowel: a e ẹ i o ọ u
language acquisition domain for learning and improving Nasal vowel: an ẹn in ọn un
knowledge of users with at least the basic/passive noesis of
Runyakitara language. The system centred on nominal
morphology, morphological analyser was used to develop
3. SYSTEM MODEL
The framework of Yoruba Computer Assisted Language Learning
exercises for learning. The system focused on nouns and made use
(YorCALL), as shown in figure 1, presents the different
of natural language processing to create extensive lesson materials
components and their interactions. Sectionalized into three, the
for prospective users of the system. Runyakitara Computer
framework can be viewed as:
Assisted Language Learning was created as a screening tool for
users, to test the users syntactic and semantic knowledge of the Front end Interactive interface (YorCALL Interface)
language, serve as access tool for learners and give relevant Modules (Palindrome, Class, Game, Learn & Dictionary) and
activity for learners. The system accomplished its intended goal Back end (YorCALL Database)
with large percentage of users showing continual interest in
RU_CALL. [14]
There is Computer Assisted Language Learning system which
consists of comprehensive wordbook consisting of Root language
(English) to Object language (Yoruba) [1]. The Language
Assistance System identifies words separated by space which is
converted to source text by lexical transfer and attaching
appropriate part of speech. The acceptable structure was achieved
by matching twenty-eight corresponding English Noun Phrase
rules with corresponding Yoruba arrangement of the rule.
Data fed into the system (in English) is pre-processed and Figure 1: YorCALL Architectural Framework
translated to corresponding data in Yoruba language. The input is
checked for its correctness using existing information in the The YorCALL interactive interface provides the user with an
database. A system with about 90 percent exactitude was produced interface to enter any Yoruba text with the use of on-Screen
and regarded as auspicious and satisfactory. keyboard or the provided buttons with Yoruba alphabets and sign.
The YorCALL Database mainly consist all the Yoruba syllable
The principles of Natural Language Processing and Digital Signal sounds as recorded by a Yoruba Language expert from Oyo town.
Processing was adopted to develop a CALL system [13]. Natural The Learn & Dictionary modules provide the users with basic
Language Processing does the breakdown of sentences into knowledge on the meaning of most common Yoruba words such
syllables, which is the smallest unit of the sentence (vowel, as cardinal and ordinal numbers from one to ten and days of the
consonant: nasal and non-nasal) by emphasizing on tones of the week and months of the year as well as English words listed in
syllables. Digital Signal Processing consists of speech processing alphabetical order from A-Z with information about them. It
and sound processing. Speech processing checks for syllables consists of 1000 English words and their equivalent in Yoruba
corresponding to input block of text and combine together to form language. Users are able to hear the corresponding pronunciation
strings and then optimizing them. The sound processing (Speech of the words. The Palindrome module responds to indicate
signal) process the sound and make the pronunciation sound whether any Yoruba word as entered by the user is/is not a
available. palindrome.
A web based Computer Assistance Language Learning on two
languages was built, to translate from Yoruba phrases to English 3.1 Class Module
Language and contra wise [14]. Poly-layer framework and Hidden The CLASS module provides principles of pronouncing words in
Markov Model were employed. Using mathematical and word Yoruba language and also provides guide on the principle of tonal
principle, Yoruba and English words were grouped into two signs and applications. It allows the user to write down words,
exclusive sets. The set theory was used to determine acceptable check for validity and pronounce the word for the user.
structure, axiom of extension, for any two subsets from source and
target languages to be equal there must be like components. The
law of probability, Bayes' theorem, and Statistical design theory
were used to increase the CALL system accuracy and produce
result.
2
3.1.2 Token/Syllable Fetcher
Each of the vowel sounds was combined with each consonant and
nasal sound to generate all possible syllable. These sounds to each
syllable were recorded using audio recorder by a Yoruba language
speaking expert. The recorded sounds were subsequently trimmed
to eliminate noise and saved in the YorCALL DB with the file
name they represent. The Token/syllable fetchers searches through
for the coreesponding audio sound for each token for stacking and
concatenation.
Figure 2: Model of the Class Module
3.1.3 Syllable to Speech Processor
After successful process of tokenisation and equivalent audio
As depicted in figure 2, YorCALL system’s processes include: sound of the syllables are fetched from the audio dataset, they are
a) breaking words into syllable stacked in the order of their entry (from left to right) and
b) fetching the audio equivalent of syllable concatenated, ready to be played by the sound player box. Users
c) stacking and concatenating sounds to produce a word sound are able to view the breakdown of words pronunced to syllable and
Users are can type in words for pronunciation by using the play the sound equivalent as often time as possible as shown in
onscreen keyboard provided or use any keyboard that allows user Figure 6.
to type Yoruba fonts. The words are broken down to syllable(s)
and equivalent audio sound of the syllable is fetched and SS1 + SS2 + SS3 …+… SSn
concatenated. After which a sound player box pops up and users
are able to play the sound. Where SS represents syllable sound
3.1.1 Tokenizer 3.2 System Class Diagram
A syllable in Yoruba can either be a vowel sound, combination of YorCALL has five classes (Class, Palindrome, Dictionary, Learn,
vowel and consonant, or nasal sound. During the process of Games) which are subclasses of the Home. The Sound Player is a
breaking words down to syllables, the tonal sounds assigned by sub class of the Class with a modal dependency. As shown in
the user is taken into consideration. Each word input by the user is Figure 4, each class has at least member methods with data
scanned through, vowel letters are the main unit is used for member ranging from zero to six.
tokenisation.
The tokenization process is broadly divided in three phases,
namely:
i. accept word
ii. scan from the left, check for vowel sounds
ii. anywhere there is a vowel sound break, and then add to syllable
set until end of the word.
Accept text
Scan accepted text
from left to right
N
End of Vowel Add to Syllable
Text? Syllable? set
N Y
Y
End
Figure 3: Flow Diagram of the tokenization process
For Illustration, if b is to be combined with the vowel sounds; it
will produce the following syllables as in table 1: Figure 4: YorCALL Class Diagram
Table 1: Some Yoruba Syllables
Consonant Vowel Sounds Syllables Produced 4. SAMPLE SCREEN SHOTS OF YORCALL
Alphabet The user enters a yoruba text with the customized keyboard
b a e ẹ i o ọ u ba be bẹ bi bo bọ bu provided as shown in Figure 2 which allows the entering of any
ẹ ọ b b bẹ b b bọ b Yoruba word. On clicking the ‘check’ button, the tokenize()
à è ẹ` ì ọ ò ù bà bè bẹ`bì bọ bò bù method is called and the inputted text is syllabilized.
an ẹn in ọn un ban bẹn bin bọn bun
n ẹn n ọn n b n bẹn b n bọn b n
àn ẹ`n ìn ọn ùn bàn bẹ`n bìn bọn bùn
⁞ ⁞ ⁞
3
Table 2: Summary of Responses to Administered
Questionnaire (Source: [13])
Weight 5 4 3 2 1
Questions VH H F L VL
X4 How would you rate the 19 30
performance of the
developed YorCALL
system?
X5 How would you rate the use 6 26 16 1
of this application?
X6 How would you rate the 6 26 13 6
voice quality produced by
the developed
system?
X7 How would you rate the sign 27 13 7 12
assignment of the Yoruba
Figure 5: The Text Input Screen alphabets display on the
screen?
X8 What is your rating of the 9 19 14 7
naturalness of the output
from the developed
YorCALL?
X9 What is your overall 6 27 13 3
performance assessment of
the developed YorCALL?
SA A N D SD
X10 Would you agree that the 10 24 12
sound produced by the
developed YORCALL was
close to Natural human
voice?
X11 Would you agree that the 17 23 9
response time (i.e. time
duration for producing
sound) was of no
significance?
X12 Would you agree that the 16 24 9
developed YorCALL system
is reliable to convert Yoruba
Figure 6: The Sound Screen text to spoken
expression?
5 PERFORMANCE MEASURE OF THE X13 Would you agree that the
developed YorCALL can
15 14 7
SYSTEM serve as a teaching aid for
Yoruba
Three category of users (amateur speakers, average Yoruba
language?
speakers, above average speakers) yielded the following
summarized responses as observed in Table 2: X14 Would you agree that the 11 25 13
developed system will be of
help to a visually challenged
person?
Key:
SA-Strongly Agree, A-Agree, N-Neutral, D-Disagree, SD-Strongly Disagree
VH-Very High, H-High, F-Fair, L-Low, VL-Very Low
4
7. ACKNOWLEDGEMENT
We appreciate all members of Intelligent System group (ISG) for
their insightful contributions towards this work.
8. REFERENCES
[1] Abiola, O. B., Adetunmbi, A. O., Fasiku, A. I., & Olatunji, K.
A. (2014). A web-based English to Yoruba noun-phrases
machine translation system.International Journal of English
Figure 7: YorCALL Performance Measure by Amateur and Literature, 5(3), 71-78.
Yoruba Speakers [2] Abidogun, B. G., & Adebule, O. I. (2013). Contributions of
mother tongue education in early Childhood
education. European Scientific Journal, ESJ,9(19).
[3]Chapelle, C.. (2009). The Relationship Between Second
Language Acquisition Theory and Computer-Assisted
Language Learning. Modern Language Journal, pp.
741–753.
[4] Davies, G. (2005, June). Computer Assisted Language
Learning: Where are we now and where are we going.
In Keynote speech at the University of Ulster Centre for
Research in Applied Languages UCALL
Figure 8: YorCALL Performance Measure by Average conference:“Developing a pedagogy for CALL (pp. 13-15).
Yoruba Speakers [5] Farmer, R., & Gruba, P. (2006). Towards model-driven
end-user development in CALL. Computer Assisted
Language Learning, 19(2-3), 149-191.
[6] Garrett, N. (1991). Technology in the service of language
learning: Trends and issues. The Modern Language
Journal, 75(1), 74-101.
[7] Garrett, N. (2009). Computer‐assisted language learning trends
and issues revisited: Integrating innovation. The Modern
Language Journal, 93(s1), 719-740.
[8] Shaalan 1, K. F. (2005). An intelligent computer assisted
language learning system for Arabic learners. Computer
Figure 9: YorCALL Performance Measure by Expert Yoruba
Assisted Language Learning, 18(1-2), 81-109.
Speakers
[9] Fagbolu, O. O., Alese, B. K., & Adewale, O. S. (2014).
The reponses of the three categories of users/Yoruba speakers
Development of a Digital Yorùbá Phrasebook on a Mobile
(amateur, average and expert) as shown by in Figures 7, 8 and 9,
Platform. In Nigerian Computer Society (NCS) 25th Annual
reveal, at both extremes, about 75% acceptability and usability of
Conference-Building a knowledge-based economy in Nigeria:
the system but only 20% voted for it to be used by the visually
The Role of Information Technology, Nike Lake Resort
challenged persons. Based on the feedback in X7,X8, X10, about
Enugu (pp. 13-19).
80% agreed that the naturalness of the system produced sound was
[10] Warschauer, M., & Healey, D. (1998). Computers and
like that of Yoruba natural speaker. 70% of the respondents
language learning: An overview. Language teaching, 31(02),
agreed that the system can be used to not only improve the
57-71.
language tonal sign assigning but also the language literacy.
[11] Arnold, W. E., & Leitzman, W. J. Review of Developments
6. CONCLUSION in Computer Assisted Language Learning. [12] Salaberry, M.
The study has presented a CALL system for Yoruba language with R. (1996). A theoretical foundation for the development of
the main objective of providing a digital learning environment that pedagogical tasks in computer mediated
introduce Yoruba language to new learner or improve amateur's communication. Calico Journal, 5-34.
knowledge, especially in the area of correct word pronunciation [13] Afolabi, A., Omidiora, E., & Arulogun, T. (2013).
and right sign assigning. Using personal computer, the system Development of text to speech system for yoruba language.
enables the user to learn at his/her own time and place. Future In Innovative Systems Design and Engineering—Special
work is ongoing to expand the number of words in the dictionary Issue of 2nd International Conference on Engineering and
and improve on present functionalities of the system such as Technology Research (Vol. 4, pp. 1-8).
development of game whereby the system pronounce Yoruba [14] Katushemererwe, F., & Nerbonne, J. (201 5). Computer-
words randomly and the user provides the textual equivalence, assisted language learning (CALL) in support of (re)-learning
considering the tone, wherby the user input is validated. In native languages: the case of Runyakitara. Computer Assisted
conclusion we believe the system can be further scaled to include Language Learning, 28(2), 112-129.
other threatened languages and taught in various levels of [15]Yoruba language. In Wikipedia, Retrieved January 21, 2015
Institutions of learning. from http://en.wikipedia.org/wiki/Yoruba_language
[16] CIA World Factbook (2001). Retrieved January 21, 2015
from http://www.cia.gov/cia/publucations/factbook.
5