The aim of this research is to develop a speech synthesis model tailored towards Nigerian languages by leveraging natural language processing tool such as FastSpeech 2 and meta-tts for high-quality, non-autoregressive text-to-speech (TTS) generation and HiFi-GAN for neural vocoding. It was motivated due to lack of high-quality synthetic speech models for low-resource languages especially Nigerian Languages and specificially Hausa, Igbo and Yoruba. The methodology adopted is a structured and iterative approach that integrates Structured System Analysis and Design Methodology (SSADM), and Machine Learning Development Lifecycle (MLDLC), which incorporates a feasibility study, corpus collection, phonetic analysis, and model training with Nigerian Language annotated speech dataset. Speech dataset will be collected and preprocess from selected Nigerian languages(Igbo Hausa and Yoruba). Phonemes will be developed using both rule-based approach and grapheme-to-phoneme models like Epitran and Phonemizer, while FastSpeech 2, meta-tts and HiFi-GAN will be fine-tuned to accommodate tonal variations and prosodic patterns inherent in these languages. The model training pipeline will integrate Tacotron-based aligners for efficient text-to-mel-spectrogram conversion, while HiFi-GAN will enhance naturalness and intelligibility. Python will be the primary programming language for the implementation of this research while the interface will be a combination of hypertext markup language (HTML), cascading style sheet (CSS) and Javascript. The expected outcome is a state-of-the-art, speech synthesis system capable of generating natural and intelligible speech across multiple Nigerian languages.
References
[1]
Akujobi, O.S. (2019) The English Language Coalescence and Multilingualism in Nigeria. IGWEBUIKE: An African Journal of Arts and Humanities, 5, 1-16.
[2]
Ren, Y., Hu, C., Tan, X., Qin, T., Zhao, S., Zhao, Z. and Liu, T.-Y. (2020) FastSpeech 2: Fast and High-Quality End-to-End Text to Speech. http://arxiv.org/abs/2006.04558
[3]
Afolabi, A., Omidiora, E. and Arulogun, T. (2013) Development of Text to Speech System for Yoruba Language. Innovative Systems Design and Engineering, 4, 1-7. https://www.iiste.org
[4]
Ekpenyong, M.E., Urua, E. and Gibbon, D. (2008) Towards an Unrestricted Domain TTS System for African Tone Languages. International Journal of Speech Technology, 11, 87-96. https://doi.org/10.1007/s10772-009-9037-5
[5]
Oyelade, J.O., Isewon, I., Famade, A. and Oyelade, J. (2022) Foundation of Computer Science FCS. International Journal of Applied Information Systems, 12.
[6]
Kong, J., Kim, J. and Bae, J. (2020) HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis. http://arxiv.org/abs/2010.05646
[7]
Ping, W., Peng, K., Zhao, K. and Song, Z. (2019) WaveFlow: A Compact Flow-Based Model for Raw Audio. http://arxiv.org/abs/1912.01219
[8]
Ngor, C.I.-A. (2024) Tone Nature of Nigerian English. African Journal of Humanities and Contemporary Education Research, 15, 399-415. https://doi.org/10.62154/e2bnwx92
[9]
Salau, A.O., Olowoyo, T.D. and Akinola, S.O. (2020) Accent Classification of the Three Major Nigerian Indigenous Languages Using 1D CNN LSTM Network Model. In: Jain, S., et al., Eds., Advances in Computational Intelligence Techniques, Springer, 1-16. https://doi.org/10.1007/978-981-15-2620-6_1
[10]
Fromont, R., Clark, L., Black, J.W. and Blackwood, M. (2023) Maximizing Accuracy of Forced Alignment for Spontaneous Child Speech.
[11]
Wu, H., Yun, J., Li, X., Huang, H. and Liu, C. (2023) Using a Forced Aligner for Prosody Research. Humanities and Social Sciences Communications, 10, Article No. 429. https://doi.org/10.1057/s41599-023-01931-4
[12]
UNESCO (2021) Towards Sustainable Preservation and Accessibility of Documentary Heritage. https://unesdoc.unesco.org/ark:/48223/pf0000380171
[13]
Tan, Y. and Jehom, W.J. (2024) The Function of Digital Technology in Minority Language Preservation: The Case of the Gyalrong Tibetan Language. Preservation, Digital Technology & Culture, 53, 165-177. https://doi.org/10.1515/pdtc-2024-0021
[14]
Hunt, A.J. and Black, A.W. (1996) Unit Selection in a Concatenative Speech Synthesis System Using a Large Speech Database. 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, Vol. 1, 373-376. https://doi.org/10.1109/icassp.1996.541110
[15]
Rabiner, L.R. and Schafer, R.W. (2007) Introduction to Digital Speech Processing. Foundations and Trends® in Signal Processing, 1, 1-194. https://doi.org/10.1561/2000000001
[16]
Bäckström, T., Räsänen, O., Zewoudie, A., Zarazaga, P.P., Koivusalo, L., Das, S., et al. (2022) Introduction to Speech Processing: 2nd Edition. https://doi.org/10.5281/ZENODO.6821775
[17]
Kuligowska, K., Kisielewicz, P. and Włodarz, A. (2018) Speech Synthesis Systems: Disadvantages and Limitations. International Journal of Engineering & Technology, 7, 234-239. https://doi.org/10.14419/ijet.v7i2.28.12933
[18]
Hande, S.S. (2014) A Review of Concatenative Text to Speech Synthesis. International Journal of Latest Technology in Engineering, Management & Applied Science, 3, 12-15. https://www.academia.edu/download/34937201/12-15.pdf
[19]
Khan, R.A., and Chitode, J.S. (2016) Concatenative Speech Synthesis: A Review. International Journal of Computer Applications, 136, 1-6. https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=dcb1aefcc8d80c90392fa9b6f2740b4516e8ec44
[20]
Wang, Y., Skerry-Ryan, R.J., Stanton, D., Wu, Y., Weiss, R.J., Jaitly, N., et al. (2017) Tacotron: Towards End-to-End Speech Synthesis. Interspeech 2017, Stockholm, 20-24 August 2017, 4006-4010. https://doi.org/10.21437/interspeech.2017-1452
[21]
Jia, Y., Zhang, Y., Weiss, R.J., Wang, Q., Shen, J., Ren, F., et al. (2018) Transfer Learning from Speaker Verification to Multispeaker Text-to-Speech Synthesis. http://arxiv.org/abs/1806.04558
[22]
Ohala, J.J. and Kawasaki, H. (1984) Prosodic Phonology and Phonetics. Phonology Yearbook, 1, 113-127. https://doi.org/10.1017/s0952675700000312
[23]
Peterson, G.E. and Shoup, J.E. (1966) A Physiological Theory of Phonetics. Journal of Speech and Hearing Research, 9, 5-67. https://doi.org/10.1044/jshr.0901.05
[24]
Pierrehumbert, J.B. (1980) The Phonology and Phonetics of English Intonation.
[25]
Fant, G. (1981) The Source Filter Concept in Voice Production. STL-QPSR, 22, 021-037. https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=647bee8e1ea9b5fcaa27dd8c0937a165a8f5f717
[26]
Ma, R., Qian, M., Fathullah, Y., Tang, S., Gales, M. and Knill, K. (2025) Cross-Lingual Transfer Learning for Speech Translation. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2, 33-43. https://doi.org/10.18653/v1/2025.naacl-short.4
[27]
Fant, G. (2001) T. Chiba and M. Kajiyama, Pioneers in Speech Acoustics. Journal of the Phonetic Society of Japan, 5, 4-5. https://doi.org/10.24467/onseikenkyu.5.2_4
[28]
Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T. and Kitamura, T. (1999) Simultaneous Modeling of Spectrum, Pitch and Duration in Hmm-Based Speech Synthesis. 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999, Budapest, 5-9 September 1999, 2347-2350.
[29]
Ping, W., Peng, K. and Chen, J. (2018) ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech. http://arxiv.org/abs/1807.07281
[30]
Atoi, N.E. (2024) Language and Communication Implication of Artificial Intelligence on Selected Nigerian University Undergraduates. UJAH: Unizik Journal of Arts and Humanities, 25, 109-154. https://doi.org/10.4314/ujah.v25i1.5
[31]
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L. and Polosukhin, I. (2017) Attention Is All You Need. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 6000-6010. http://arxiv.org/abs/1706.03762
[32]
Bleyan, H., Ritchie, S., Mortensen, J.F. and Esch, D.V. (2019) Developing Pronunciation Models in New Languages Faster by Exploiting Common Grapheme-to-Phoneme Correspondences across Languages. Interspeech 2019, Graz, 15-19 September 2019, 2100-2104. https://doi.org/10.21437/interspeech.2019-1781
[33]
Hassana, I.L. and Sanusi, M. (2019) Text to Speech Synthesis System in Yoruba Language. International Journal of Advances in Scientific Research and Engineering, 5, 180-191. https://doi.org/10.31695/ijasre.2019.33568
[34]
Olaniyan, O.M. and Akinode, V. (2023) Development of a Text-to-Speech Synthesis for Yoruba Language Using Deep Learning. Technology and Innovation, 2, 1-7.
[35]
Shen, J., Pang, R., Weiss, R.J., Schuster, M., Jaitly, N., Yang, Z., et al. (2017) Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. http://arxiv.org/abs/1712.05884
[36]
Artetxe, M., Ruder, S. and Yogatama, D. (2020) On the Cross-Lingual Transferability of Monolingual Representations. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, July 2020, 4623-4637. https://doi.org/10.18653/v1/2020.acl-main.421
[37]
Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., et al. (2020) Unsupervised Cross-Lingual Representation Learning at Scale. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, July 2020, 8440-8451. https://doi.org/10.18653/v1/2020.acl-main.747
[38]
van den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., et al. (2016) WaveNet: A Generative Model for Raw Audio. http://arxiv.org/abs/1609.03499
