Arabic Speech Recognition Systems

AbuZeina, Dia; Elshafei, Moustafa

doi:10.1007/978-1-4614-1213-7_2

Cited by 7 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transcriptions for interviews add further burden to the researcher (Stewart, Shamdasani, & Rook, 2007). Because Arabic speech recognition systems, that transform speech to text, are still facing many challenges (AbuZeina & Elshafei, 2012;Menacer et al, 2017), the researcher decided to avoid transcription and instead record summary notes, which may cause bias in summarisation, but the researcher will check the audio recordings to obtain clarifications and augment the notes.…”

Section: Research Limitationsmentioning

confidence: 99%

Enhancing Employability and e-Business Capacities for Arabic-Speaking Residents of Australia through START Online Training

Hanna

Conner

Sweeney

2020

ssp

View full text Add to dashboard Cite

Background: Arabic minority groups in Australia face language barriers and shortage of computer skills, which cause unemployment and/or an inability to establish their own businesses. The unemployment rate for this group is ~ 20.5%, which is 3-times higher than the average unemployment rate in Australia (~7%). The unemployment will get worse due to COVID-19 pandemic. The current provision of computer and language training in Australia is in English, which results in longer training times and higher chances of non-completion. Objective: The Smart Training for Arabic Residents on Technology (START) is an interventional online bi-lingual training that assists Arabic-speaking residents of Australia to establish an online business with minimum resources (money, space, and infrastructure) or at least help them find suitable employment. Methods: START uses Design-Based Research DBR, as it has its own progressive refinement approach. Both qualitative methods (skills assessment interviews, semi-guided observation, and final follow-up interviews) and quantitative methods (practical tests, log analysis/learning analytics, feedback surveys) contribute to evaluation and improvement cycles. Discussion: DBR has not been applied to vocational immigrant education previously. This research project contributes to a better understanding of the relationships between educational theory, designed learning and outcomes, to help advance learning and teaching environments by refining critical factors that lead to success for trainees. Practically, Arabic residents are provided opportunities to master computer and English skills for establishing their own online businesses. This research, however, has some limitations. Usually a team of teacher, learning designer, and researcher is recommended for DBR, but that is not possible in this PhD study. It is also acknowledged that although this study aims for optimal refinement of the START program, through multiple cycles of improvement, realistically it will be difficult to “recreate” the exact learning environment in future programs.

show abstract

Section: Research Limitationsmentioning

confidence: 99%

Enhancing Employability and e-Business Capacities for Arabic-Speaking Residents of Australia through START Online Training

Hanna

Conner

Sweeney

2020

ssp

View full text Add to dashboard Cite

show abstract

“…Recently, speech recognition is one of the technology trends. Using this technology, a machine can recognize a person's voice and understand regarding to what the person said [2,5,10].…”

Section: Introductionmentioning

confidence: 99%

“…work of the Dragon System at Carnegie Mellon University (Baker 1975), the longstanding effort of IBM on a voice-dictation system (Averbuch et al 1987; Bahl, Jelinek, and Mercer 1983; Jelinek 1976), etc [11]. Main inference which is used by HMM is Bayes' Rule that is also used in Naïve Bayes [10], a part of Bayesian Network. This system will focus on Naïve Bayes and Bayesian Network.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Naïve Bayes and Bayesian Network on The Classification of Hijaiyah Pronunciation with Punctuation Letters

Adiwijaya

Riyani²,

Mubarok

2019

Proceedings of the 2018 International Conference on Industrial Enterprise and System Engineering (IcoIESE 2018)

View full text Add to dashboard Cite

Arabic is a unique language because it really concerns in makhraj (the way of sound is made) that differentiate letters and words. The difference in pronouncing letters and words make the meaning of those words different, because pronuncation in Qur'an letters really concern in harakat (the length of words). According to that matter, it is necessary to build a speech recognition for Hijaiyah with punctuation letters in Qur'an. There are many methods that can be used for building that system. One of the best method is Hidden Markov Model (HMM). Main inference in HMM is Bayes' Rule. Bayes' Rule also used in Naïve Bayes, a part of Bayesian Network. This paper focused on Naïve Bayes and Bayesian Network. Before recognizing the data, first the data will be pre-processed using Linear Predictive Coding (LPC) for extracting cepstral coefficient that will be used as input in classifier. This system give a best micro average F1 score result, 76,67%, with Bayesian Network.

show abstract

“…On the other hand, a lot of users and languages' speakers eliminate them from the current written text. In detail, words with similar form of writing may be discerned via their context by several Arab readers [1]. Both of the Arabic language and Islam simultaneously spread in the Middle East, primarily in the course of the 6th and 7th centuries.…”

Section: Introductionmentioning

confidence: 99%

Generating Arabic Stop-Word for Hadith

Hazzaimeh¹,

Norwawi²,

Khalaf³

2019

MJoSHT

View full text Add to dashboard Cite

Stop-words or (function words) play a great role in performing various functions in sentences, but are still typically inadequate to use for retrieval. They consist of several elements such as common nouns, pronouns and prepositions. With that, there are several Arabic particles available in the online Khoja and Abu EL-Khair stoplist taken from various websites. Arabic stop-words’ main problem lies in accepting the prefixes and suffixes’ attachment. In the current paper, a new methodology for generating a general stop-word list has been proposed and applied on hadiths. In detail, hadith is defined as words, acts, deeds, traditions, silent approvals and character of Prophet Muhammad S.A.W. (peace be upon him). The current paper aims at examining the effect of removing stopwords from verification of hadiths. The problem is that the previously generated stop-word lists have been on Modern Standard Arabic (MSA), which is the most commonly used language in hadiths. A stop-word list of Hadith and a corpus-based list has been created to be used in the process of hadith verification. The effectiveness and success of Hadith verification when using the newly generated lists along with earlier generated lists of MSA, combining the Hadith lists have been compared with the MSA lists. The Hadith verification has been performed using sequential pattern mining. Lastly, the experiments have demonstrated that the general lists comprising hadith words showed a better performance compared to using the lists of MSA stopwords.

show abstract

Arabic Speech Recognition Systems

Cited by 7 publications

References 37 publications

Enhancing Employability and e-Business Capacities for Arabic-Speaking Residents of Australia through START Online Training

Enhancing Employability and e-Business Capacities for Arabic-Speaking Residents of Australia through START Online Training

A Comparison of Naïve Bayes and Bayesian Network on The Classification of Hijaiyah Pronunciation with Punctuation Letters

Generating Arabic Stop-Word for Hadith

Contact Info

Product

Resources

About