With the rising demand for inclusive communication, there is an urgent need for robust systems capable of interpreting and translating sign language gestures. Such systems enhance inclusivity, fostering better interaction both among Deaf and Hard of Hearing individuals and with the broader community. An effective sign language recognition system should accurately interpret hand gestures, facial expressions, and body movements to recognize the intended word. This work focuses on developing a Sign Language Recognition system that uses American Sign Language (ASL) and Indian Sign Language (ISL) as inputs, chosen for their widespread use and large number of users globally. The proposed Bilingual Sign Language Recognition System detects landmarks through computer vision algorithms and applies keyframe extraction. A Long Short-Term Memory (LSTM) network then processes these frames to capture spatial and temporal features essential to sign language. The identified word is then displayed to the user. Currently, the system recognizes individual words rather than complete sentences. Leveraging deep learning and extensive datasets, this framework aims to create a more accessible world for people with hearing impairments.