Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175923,
        author = {Sanika Chaudhari and Vinaya Kulkarni and Pranoti Kale and Shruti Bhumkar and Manasi Deshmukh and Samruddhi Deshmukh},
        title = {Next-Gen Communication: LSTM-Powered Speech-to-Sign Language Translation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {4410-4415},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175923},
        abstract = {Deaf and Hard of Hearing (DHH) individuals experience a lot of difficulties and are deprived of access to video material. Due to the increasing demand for audio-visual communication, this makes it difficult for the DHH community to access the material. Owing to the high use of audio-visual content delivery in contemporary society hampers the DHH community’s accessibility to the content being passed across. Addressing the above issues, our system overcomes the Communication barrier by applying highly advanced AI-based video translation methods that translate spoken content to Sign Language through GIFs, making it a more natural and accessible experience to the users. Our framework integrates diverse algorithms, including Sequence-to-sequence (Seq2seq), and Long Short-Term Memory (LSTM) – a type of Recurrent Neural Network. This approach aims to capitalize on the strengths of individual models, optimizing the overall performance.},
        keywords = {Sign Language Translation, Video Processing, Audio Extraction, Audio-to-Text Conversion, Text Preprocessing, Contextual Analysis with BERT, Gesture Synchronization, LSTM Networks, Speech Recognition, Natural Language Processing (NLP).},
        month = {April},
        }