Natural speaker-independent Arabic speech recognition system based on Hidden Markov Models using Sphinx tools

Abushariah, Mohammad A. M.; Ainon, Raja Noor; Zainuddin, Roziati; Elshafei, Moustafa; Khalifa, Othman O.

doi:10.1109/iccce.2010.5556829

Cited by 41 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many Arabic ASR researchers use different learning algorithms such as Hidden Markov Models (HMM), SVM and hybrid from multi-system (Zarrouk et al, 2014) and (Ali et al, 2015b). For effective natural speaker-independent Arabic continuous speech recognition, (Abushariah et al, 2010)implementation, and evaluation of a research work for developing a high performance natural speakerindependent Arabic continuous speech recognition system. It aims to explore the usefulness and success of a newly developed speech corpus, which is phonetically rich and balanced, presenting a competitive approach towards the development of an Arabic ASR system as compared to the state-of-the-art Arabic ASR researches.…”

Section: Speech Recognition System (Srs)mentioning

confidence: 99%

Handicapped Wheelchair Movements Using Discrete Arabic Command Recognition

Nahar¹

2020

SJKFU

View full text Add to dashboard Cite

Automatic Speech Recognition (ASR) is an effective and widespread method used to interpret the human voice into commands. Over the past few decades and due to the great evolution in data science, the processing of speech has been embedded in various new technologies. The benefits of such evolution motivated us to develop a discrete voice system for controlling the wheelchair movements for Arab people with physical impairment (handicapped people). The wheelchair via voice system was able to recognize seven isolated words in the Arabic language. The approach uses the CMU-Sphinx4 ASR for evaluating the effectiveness and the accuracy of the recognition system. A corpus was built, and then the system was trained on 70% of this corpus and tested using the rest of 30%. The experiments reveal that the recognition rate of the proposed approach is 96%. The average level of accuracy of the real experiment and corpus-based testing experiment reached 94%.

show abstract

Section: Speech Recognition System (Srs)mentioning

confidence: 99%

Handicapped Wheelchair Movements Using Discrete Arabic Command Recognition

Nahar¹

2020

SJKFU

View full text Add to dashboard Cite

show abstract

“…Stock market prediction is highly related to time series models such as Hidden Markov models (HMMs) [40,2,15,34] and deep LSTM networks [60]. Hassan and Nath [21] use HMM to predict the closing price on the next day of airline stocks.…”

Section: Related Workmentioning

confidence: 99%

Enhancing stock market prediction with extended coupled hidden Markov model over multi-sourced data

Zhang

Wang

et al. 2018

Knowl Inf Syst

View full text Add to dashboard Cite

Traditional stock market prediction methods commonly only utilize the historical trading data, ignoring the fact that stock market fluctuations can be impacted by various other information sources such as stock related events. Although some recent works propose event-driven prediction approaches by considering the event data, how to leverage the joint impacts of multiple data sources still remains an open research problem. In this work, we study how to explore multiple data sources to improve the performance of the stock prediction. We introduce an Extended Coupled Hidden Markov Model incorporating the news events with the historical trading data. To address the data sparsity issue of news events for each single stock, we further study the fluctuation correlations between the stocks and incorporate the correlations into the model to facilitate the prediction task. Evaluations on China A-share market data in 2016 show the superior performance of our model against previous methods.

show abstract

“…However, from speaker-independence perspective, [19,20], a total of 8043 utterances were used resulting in about 8 hours of speech data collected from 8 (5 male and 3 female) Arabic native speakers from 6 different Arab countries namely Jordan, Palestine, Egypt, Sudan, Algeria, and Morocco as mentioned earlier. The leave-one-out cross validation and testing approach was applied, where every round speech data of 7 out of 8 speakers were trained and speech data of the 8th were tested.…”

Section: Modifications Using Basic Parameters At Training Levelmentioning

confidence: 99%