EUVIMEDEUVIMED entdecken
Crossref

A Multilingual AI-Powered Bidirectional Communication System with Real Time Translations and Voice output

Kushagra Dwivedi, Rohit Mishra, Ashutosh Kumar Singh, Pradumya Kumar, Ayushman Pandey, Prachi Pandey, Nitesh Kumar Maurya

International Journal of Drug Delivery Technology · 29.05.2026 · 16 (40s)

DOI: 10.25258/ijddt.16.40s.17 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 29.05.2026. Verfasst von Kushagra Dwivedi und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In multilingual cultures, communication isstill challenging due to linguistic disparities, particularly when individuals speak different native tongues. The natural flow of communication is disrupted by the majority of current translation technologies, which rely on text and don't function well in real-time talks. In order to improve the naturalness and smoothness of talks, this study presents a real-time, two-way voice translation system. It performs through an end-to-end AI pipeline, which unites speech synthesis (TTS), translation (NMT), and speech recognition (ASR) into a single system. Due to this, it is also able to process speech real-time and translate text and audio with a latency of a minimum. In order to provide quick, lowlatency communication, the system is connected via WebSockets and created utilizing a React.js and FastAPI architecture. It also adds intelligent enhancements such as sentence-aware chunking, speech activity, transcript cleanup, and asynchronous processing to make it much faster and more accurate. There is also an option of users reviewing past chat and updating transcripts real time. Tests on five Indian language pairs with high accuracy, low mistake rates with less than a second reaction times are strong and therefore competitive with popular programs such as Google and Microsoft Translator. The system is commendable in all aspects, as it has the ability to support organic, two-way conversations with both text and voice outputs at the same time. It can be improved in the future to accommodate more low-resource languages, operate offline, handle high-noise environments better, and even have a voice of a speaker. These additions make it have much potential in application in various areas such as emergency response, healthcare, education, and legal services.

Zitieren

APA

Dwivedi, K., Mishra, R., Singh, A. K., Kumar, P., Pandey, A., Pandey, P., & Maurya, N. K. (2026). A Multilingual AI-Powered Bidirectional Communication System with Real Time Translations and Voice output. International Journal of Drug Delivery Technology, 16(40s). https://doi.org/10.25258/ijddt.16.40s.17

Vancouver

Dwivedi K, Mishra R, Singh AK, Kumar P, Pandey A, Pandey P, et al. A Multilingual AI-Powered Bidirectional Communication System with Real Time Translations and Voice output. International Journal of Drug Delivery Technology. 2026;16(40s). doi:10.25258/ijddt.16.40s.17

BibTeX
@article{Dwivedi2026,
  author = {Dwivedi, Kushagra and Mishra, Rohit and Singh, Ashutosh Kumar and Kumar, Pradumya and Pandey, Ayushman and Pandey, Prachi and Maurya, Nitesh Kumar},
  title = {A Multilingual AI-Powered Bidirectional Communication System with Real Time Translations and Voice output},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {40s},
  doi = {10.25258/ijddt.16.40s.17}
}
Kostenlos starten →