Impact of a Newly Developed Modern Standard Arabic Speech Corpus on Implementing and Evaluating Automatic Continuous Speech Recognition Systems

Abushariah, Mohammad A. M.; Ainon, Raja Noor; Zainuddin, Roziati; Al-Qatab, Bassam Ali; Alqudah, Assal Ali Mustafa

doi:10.1007/978-3-642-16202-2_1

Cited by 6 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. The best combination for the first development phase was found to be 16 for the Gaussian mixture distributions and 400 for senones [18,20]. Based on this combination, results of the above three data sets are presented in Table 11.…”

Section: Modifications Using Basic Parameters At Training Levelmentioning

confidence: 97%

“…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%

See 1 more Smart Citation

Modern standard Arabic speech corpus for implementing and evaluating automatic continuous speech recognition systems

Abushariah

Ainon

Zainuddin

et al. 2012

Journal of the Franklin Institute

Self Cite

View full text Add to dashboard Cite

Section: Modifications Using Basic Parameters At Training Levelmentioning

confidence: 97%

Section: Modifications Using Basic Parameters At Training Levelmentioning

confidence: 99%

Modern standard Arabic speech corpus for implementing and evaluating automatic continuous speech recognition systems

Abushariah

Ainon

Zainuddin

et al. 2012

Journal of the Franklin Institute

Self Cite

View full text Add to dashboard Cite

“…A. M. Abushariah et al [154] came up with a system that recognized the English digits using MATLAB. They used MFCC for feature extraction and HMM for the recognition.…”

Section: Related Research On Speech Based Human Robot Interactionmentioning

confidence: 99%

An efficient gesture based humanoid learning using wavelet descriptor and MFCC techniques

Baranwal

Nandi

2016

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Today robotics is a vibrant field of research and it has tremendous application potentials not only in the area of industrial environment, battle field, construction industry and deep sea exploration but also in the household domain as a humanoid social robot. To be accepted in the household, the robots must have a higher level of intelligence and they must be capable of interacting people socially around it who is not supposed to be robot specialist. All these come under the field of human robot interaction (HRI). Our hypothesis is-"It is possible to design a multimodal human robot interaction framework, to effectively communicate with Humanoid Robots". In order to establish the above hypothesis speech and gesture have been XVII Dissertation Publications

show abstract

“…expensive, lacking adaptability, reusability, quality, coverage, and adequate information types (Abushariah et al 2010).…”

mentioning

confidence: 99%

Investigating the effects of gender, dialect, and training size on the performance of Arabic speech recognition

Alsharhan

Ramsay

2020

Lang Resources & Evaluation

View full text Add to dashboard Cite

Research in Arabic automatic speech recognition (ASR) is constrained by datasets of limited size, and of highly variable content and quality. Arabic-language resources vary in the attributes that affect language resources in other languages (noise, channel, speaker, genre), but also vary significantly in the dialect and level of formality of the spoken Arabic they capture. Many languages suffer similar levels of cross-dialect and cross-register acoustic variability, but these effects have been under-studied. This paper is an experimental analysis of the interaction between classical ASR corpus-compensation methods (feature selection, data selection, gender-dependent acoustic models) and the dialect-dependent/register-dependent variation among Arabic ASR corpora. The first interaction studied in this paper is that between acoustic recording quality and discrete pronunciation variation. Discrete pronunciation variation can be compensated by using grapheme-based instead of phone-based acoustic models, and by filtering out speakers with insufficient training data; the latter technique also helps to compensate for poor recording quality, which is further compensated by eliminating delta-delta acoustic features. All three techniques, together, reduce Word Error Rate (WER) by between 3.24% and 5.35%. The second aspect of dialect and register variation to be considered is variation in the fine-grained acoustic pronunciations of each phoneme in the language. Experimental results prove that gender and dialect are the principal components of variation in speech, therefore, building gender and dialect-specific models leads to substantial decreases in WER. In order to further explore the degree of acoustic differences between phone models required for each of the dialects of Arabic, cross-dialect experiments are conducted to measure how far apart Arabic dialects are acoustically in order to make a better decision about the minimal number of recognition systems needed to cover all dialectal Arabic. Finally, the research addresses an important question: how much training data is needed for building efficient speaker-independent ASR systems? This includes developing some learning curves to find out how large must the training set be to achieve acceptable performance.

show abstract

Impact of a Newly Developed Modern Standard Arabic Speech Corpus on Implementing and Evaluating Automatic Continuous Speech Recognition Systems

Cited by 6 publications

References 2 publications

Modern standard Arabic speech corpus for implementing and evaluating automatic continuous speech recognition systems

Modern standard Arabic speech corpus for implementing and evaluating automatic continuous speech recognition systems

An efficient gesture based humanoid learning using wavelet descriptor and MFCC techniques

Investigating the effects of gender, dialect, and training size on the performance of Arabic speech recognition

Contact Info

Product

Resources

About