Arabic Phonemes Transcription Using Learning Vector Quantization: 'Towards the Development of Fast Quranic Text Transcription'

Khalid M.O. Nahar; Wasfi G. Al-Khatib; Moustafa Elshafei; Husni Al-Muhtaseb; Mansour M. Alghamdi

doi:10.1109/NOORIC.2013.85

Arabic Phonemes Transcription Using Learning Vector Quantization: 'Towards the Development of Fast Quranic Text Transcription'

Khalid M.O. Nahar, Wasfi G. Al-Khatib, Moustafa Elshafei, Husni Al-Muhtaseb, Mansour M. Alghamdi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

In this paper, we investigated the use of Learning Vector Quantization (LVQ) for phoneme transcription in Arabic speech recognition systems. We used Arabic speech corpus of TV news clips. Then, we employed feature vectors, which embed the frame neighboring correlation information between adjacent phonemes to replace the traditional trip hones models. Next, we generated the phonemes codebooks using the K-means splitting algorithm. After that, we trained the generated codebooks using the LVQ algorithm. When using the trained LVQ codebooks in utterance phoneme transcription of an open vocabulary test corpus, the phoneme recognition rate was 72% without the use of any added phoneme big rams or HMM models. The results of this research if improved could be used to serve the holy Quran text transcription without any phonemes big rams (phonemes language model). This would increase the speed of the Quranic speech to text transcription and creates the infrastructure of suitable high speed automatic identification system of Quranic sounds recognition and translation.

Original language	English
Title of host publication	Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	407-412
Number of pages	6
ISBN (Electronic)	9781479928231
DOIs	https://doi.org/10.1109/NOORIC.2013.85
State	Published - 25 Sep 2015

Publication series

Name	Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Keywords

K-means
LVQ
Quranic Speech Recognition
codebooks
phoneme bigrams

ASJC Scopus subject areas

Information Systems

Access to Document

10.1109/NOORIC.2013.85

Cite this

Nahar, K. M. O., Al-Khatib, W. G., Elshafei, M., Al-Muhtaseb, H., & Alghamdi, M. M. (2015). Arabic Phonemes Transcription Using Learning Vector Quantization: 'Towards the Development of Fast Quranic Text Transcription'. In Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013 (pp. 407-412). Article 7277283 (Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NOORIC.2013.85

Nahar, Khalid M.O. ; Al-Khatib, Wasfi G. ; Elshafei, Moustafa et al. / Arabic Phonemes Transcription Using Learning Vector Quantization : 'Towards the Development of Fast Quranic Text Transcription'. Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 407-412 (Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013).

@inproceedings{a56f40c765cf460e84fd74ca0bcc3491,

title = "Arabic Phonemes Transcription Using Learning Vector Quantization: 'Towards the Development of Fast Quranic Text Transcription'",

abstract = "In this paper, we investigated the use of Learning Vector Quantization (LVQ) for phoneme transcription in Arabic speech recognition systems. We used Arabic speech corpus of TV news clips. Then, we employed feature vectors, which embed the frame neighboring correlation information between adjacent phonemes to replace the traditional trip hones models. Next, we generated the phonemes codebooks using the K-means splitting algorithm. After that, we trained the generated codebooks using the LVQ algorithm. When using the trained LVQ codebooks in utterance phoneme transcription of an open vocabulary test corpus, the phoneme recognition rate was 72% without the use of any added phoneme big rams or HMM models. The results of this research if improved could be used to serve the holy Quran text transcription without any phonemes big rams (phonemes language model). This would increase the speed of the Quranic speech to text transcription and creates the infrastructure of suitable high speed automatic identification system of Quranic sounds recognition and translation.",

keywords = "K-means, LVQ, Quranic Speech Recognition, codebooks, phoneme bigrams",

author = "Nahar, {Khalid M.O.} and Al-Khatib, {Wasfi G.} and Moustafa Elshafei and Husni Al-Muhtaseb and Alghamdi, {Mansour M.}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.",

year = "2015",

month = sep,

day = "25",

doi = "10.1109/NOORIC.2013.85",

language = "English",

series = "Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "407--412",

booktitle = "Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013",

address = "United States",

}

Nahar, KMO, Al-Khatib, WG, Elshafei, M, Al-Muhtaseb, H & Alghamdi, MM 2015, Arabic Phonemes Transcription Using Learning Vector Quantization: 'Towards the Development of Fast Quranic Text Transcription'. in Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013., 7277283, Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013, Institute of Electrical and Electronics Engineers Inc., pp. 407-412. https://doi.org/10.1109/NOORIC.2013.85

Arabic Phonemes Transcription Using Learning Vector Quantization: 'Towards the Development of Fast Quranic Text Transcription'. / Nahar, Khalid M.O.; Al-Khatib, Wasfi G.; Elshafei, Moustafa et al.
Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013. Institute of Electrical and Electronics Engineers Inc., 2015. p. 407-412 7277283 (Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Arabic Phonemes Transcription Using Learning Vector Quantization

T2 - 'Towards the Development of Fast Quranic Text Transcription'

AU - Nahar, Khalid M.O.

AU - Al-Khatib, Wasfi G.

AU - Elshafei, Moustafa

AU - Al-Muhtaseb, Husni

AU - Alghamdi, Mansour M.

PY - 2015/9/25

Y1 - 2015/9/25

N2 - In this paper, we investigated the use of Learning Vector Quantization (LVQ) for phoneme transcription in Arabic speech recognition systems. We used Arabic speech corpus of TV news clips. Then, we employed feature vectors, which embed the frame neighboring correlation information between adjacent phonemes to replace the traditional trip hones models. Next, we generated the phonemes codebooks using the K-means splitting algorithm. After that, we trained the generated codebooks using the LVQ algorithm. When using the trained LVQ codebooks in utterance phoneme transcription of an open vocabulary test corpus, the phoneme recognition rate was 72% without the use of any added phoneme big rams or HMM models. The results of this research if improved could be used to serve the holy Quran text transcription without any phonemes big rams (phonemes language model). This would increase the speed of the Quranic speech to text transcription and creates the infrastructure of suitable high speed automatic identification system of Quranic sounds recognition and translation.

AB - In this paper, we investigated the use of Learning Vector Quantization (LVQ) for phoneme transcription in Arabic speech recognition systems. We used Arabic speech corpus of TV news clips. Then, we employed feature vectors, which embed the frame neighboring correlation information between adjacent phonemes to replace the traditional trip hones models. Next, we generated the phonemes codebooks using the K-means splitting algorithm. After that, we trained the generated codebooks using the LVQ algorithm. When using the trained LVQ codebooks in utterance phoneme transcription of an open vocabulary test corpus, the phoneme recognition rate was 72% without the use of any added phoneme big rams or HMM models. The results of this research if improved could be used to serve the holy Quran text transcription without any phonemes big rams (phonemes language model). This would increase the speed of the Quranic speech to text transcription and creates the infrastructure of suitable high speed automatic identification system of Quranic sounds recognition and translation.

KW - K-means

KW - LVQ

KW - Quranic Speech Recognition

KW - codebooks

KW - phoneme bigrams

UR - http://www.scopus.com/inward/record.url?scp=84964957499&partnerID=8YFLogxK

U2 - 10.1109/NOORIC.2013.85

DO - 10.1109/NOORIC.2013.85

M3 - Conference contribution

AN - SCOPUS:84964957499

T3 - Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013

SP - 407

EP - 412

BT - Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Nahar KMO, Al-Khatib WG, Elshafei M, Al-Muhtaseb H, Alghamdi MM. Arabic Phonemes Transcription Using Learning Vector Quantization: 'Towards the Development of Fast Quranic Text Transcription'. In Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013. Institute of Electrical and Electronics Engineers Inc. 2015. p. 407-412. 7277283. (Proceedings - 2013 Taibah University International Conference on Advances in Information Technology for the Holy Quran and Its Sciences, NOORIC 2013). doi: 10.1109/NOORIC.2013.85

Arabic Phonemes Transcription Using Learning Vector Quantization: 'Towards the Development of Fast Quranic Text Transcription'

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this