The week's pick
Random Articles
Reseach Article
GlobalSpeak: Seamless Cross-Language Communication via Earpiece
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 55 |
| Year of Publication: 2025 |
| Authors: Aditya Tripathi, Siddhi Vesawkar, Ansh Vishwakarma, Jignesh Patel |
10.5120/ijca2025925930
|
Aditya Tripathi, Siddhi Vesawkar, Ansh Vishwakarma, Jignesh Patel . GlobalSpeak: Seamless Cross-Language Communication via Earpiece. International Journal of Computer Applications. 187, 55 ( Nov 2025), 1-11. DOI=10.5120/ijca2025925930
Abstract
Language barrier are a big difficulty for tourists in foreign locations, sometimes resulting in misinterpretation and inconvenience. Although there are mobile-based translation applications such as Google Translate, they need continuous user engagement and are not appropriate for hands-free, real-time communications. Despite their effectiveness, wearable translators are expensive and unavailable to the majority of users. This paper presents "GlobalSpeak," a low-cost real-time translation system that offers smooth, two-way speech translation using Bluetooth earbuds and a mobile/web application. Using APIs like Google Speech-to-Text, Google Translate and text-to-speech engines, the system integrates speech recognition, machine translation and text-to-speech modules. GlobalSpeak facilitates natural conversation flow without the need for human intervention because to its simple user interface and dynamic audio routing. This approach is intended to improve international cooperation, emergency help and tourism communication.
References
- Google Cloud, "Cloud Translation API Documentation", [Online]. Available: https://cloud.google.com/translate
- Google Cloud, "Speech-to-Text API Documentation", [Online]. Available: https://cloud.google.com/speech-to-text
- Timekettle Technologies, “WT2 Edge Translator,” [Online]. Available: https://www.timekettle.co
- G. Klein, Y. Kim, Y. Deng, J. Senellart and A. M. Rush, “OpenNMT: Open-Source Toolkit for Neural Machine Translation,” in Proc. ACL, 2017, pp. 67–72.
- M. Ott, S. Edunov, A. Baevski, et al., “fairseq: A Fast, Extensible Toolkit for Sequence Modeling,” in Proc. NAACL-HLT, 2019, pp. 48–53.
- N. Jaitly and G. Hinton, “Vocal tract length perturbation (VTLP) improves speech recognition,” in Proc. ICML Workshop on Deep Learning for Audio, Speech and Language, 2013.
- D. Amodei et al., “Deep Speech 2: End-to-End Speech Recognition in English and Mandarin,” in Proc. ICML, 2016.
- A. Vaswani et al., “Attention Is All You Need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017.
- R. K. Sharma and S. K. Yadav, “A Review on Real-Time Speech Translation Systems,” IEEE ICCCA, 2021.
- Y. Lu, Y. Jiang and Z. Zhang, “Real-Time Multilingual Speech Translation with Deep Learning,” IEEE Transactions on Audio, Speech and Language Processing, vol. 28, pp. 1123–1135, 2020.
- R. Garg and P. Joshi, “Offline Speech Recognition and Translation using Transformer Models,” 2023 IEEE Conference on Computational Intelligence and Communication Networks (CICN), pp. 303–308
Index Terms
Keywords