Speech-to-Text Conversion in Indonesian Language Using a Deep Bidirectional Long Short-Term Memory Algorithm

被引：0

作者：

Dwijayanti S. ^{[1
]}

Tami M.A. ^{[1
]}

Suprapto B.Y. ^{[1
]}

机构：

[1] Department of Electrical Engineering, Universitas Sriwijaya, Indralaya

来源：

Intl. J. Adv. Comput. Sci. Appl. | 2021年 / 3卷 / 225-230期

关键词：

Deep Bidirectional Long ShortTerm Memory (LSTM); Mel frequency cepstral coefficients (MFCC); spectrogram; Speech-to-text; word error rate;

D O I：

10.14569/IJACSA.2021.0120327

中图分类号：

学科分类号：

摘要：

Now-a-days, speech is used also for communication between humans and computers, which requires conversion from speech to text. Nevertheless, few studies have been performed on speech-to-text conversion in Indonesian language, and most studies on speech-to-text conversion were limited to the conversion of speech datasets with incomplete sentences. In this study, speech-to-text conversion of complete sentences in Indonesian language is performed using the deep bidirectional long short-term memory (LSTM) algorithm. Spectrograms and Mel frequency cepstral coefficients (MFCCs) were utilized as features of a total of 5000 speech data spoken by ten subjects (five males and five females). The results showed that the deep bidirectional LSTM algorithm successfully converted speech to text in Indonesian. The accuracy achieved by the MFCC features was higher than that achieved with the spectrograms; the MFCC obtained the best accuracy with a word error rate value of 0.2745% while the spectrograms were 2.0784%. Thus, MFCCs are more suitable than spectrograms as feature for speech-to-text conversion in Indonesian. The results of this study will help in the implementation of communication tools in Indonesian and other languages. © 2021. All Rights Reserved.

引用

页码：225 / 230

页数：5

共 23 条

[1]

Gold B., Morgan N., Ellis D., Speech and Audio Signal Processing, (2011)

[2]

Khilari P., Bhope V. P., A review on speech to text conversion, Int. J. Adv. Res. Comput. Eng. Technol, 4, 7, pp. 3067-3072, (2015)

[3]

Deng L., Et al., Recent advances in deep learning for speech research at microsoft, 2013 IEEE Internatsional Conference on Acoustics, Speech and Signal Processing, 26, 64, pp. 8604-8608, (2013)

[4]

Munir A., Kashif Ehsan S., Mohsin Raza S. M., Mudassir M., Face and speech recognition based smart home, 2019 Int. Conf. Eng. Emerg. Technol. ICEET, pp. 1-5, (2019)

[5]

Jeyalakshml C., Speech recognition of deaf and hard of hearing people using hybrid neural network, 2010 2nd Int. Conf. Mech. Electron. Eng, I, pp. 83-87, (2010)

[6]

Ahmed B. H. A., Ghabayen A. S., Arabic automatic speech recognition enhancement, Palest. Int. Conf. Inf. Commun. Technol. Arab, pp. 98-102, (2017)

[7]

Hotta H., Japanese speaker-independent homonyms speech recognition, Procedia - Soc. Behav. Sci, 27, pp. 306-313, (2011)

[8]

Othman Z. A., Razak Z., Abdullah N. A., Yakub M., Bin Zulkifli Z., Jawi character speech-to-text engine using linear predictive and neural network for effective reading, Proc. - 2009 3rd Asia Int. Conf. Model. Simulation, AMS 2009, pp. 348-352, (2009)

[9]

Kumar A., Dua M., Choudhary T., Continuous hindi speech recognition using monophone based acoustic modeling, Int. Conf. Adv. Comput. Eng. Appl, pp. 1-5, (2014)

[10]

Laksono T. P., Hidayatullah A.F., Ratnasari C.I., Speech to text of patient complaints for Bahasa Indonesia, 2018 International Conference on Asian Languange Processing (IALP), pp. 79-84, (2018)

← 1 2 3 →