Talk · AIP conference proceedings · January 1, 2024
Text processing technology in Uzbek speech to sign language translation systems
Muhammadjon Musaev, Dilshod Juraev, Mannon Ochilov, Malika Abdullaeva
Abstract
This article analyzes methods for developing systems that translate speech into sign language. It describes the main sequence employed in these translation systems, focusing on the methods and algorithms used in speech recognition and translation modules for sign language. The core of this process occurs during the stages of natural language processing, which involve tokenization, stemming, lemmatization, syntactic analysis (parsing), and grammatical tagging of parts of speech (POS-tagging). The sequence proposed in the article details the procedure for translating speech or text into sign sentences using natural language processing techniques. Additionally, the steps of dataset formation for the proposed translation system and the evaluation results of generating gesture video animations based on sign language grammar are presented.
More by Mannon Ochilov
- PadSink-Track: A Calibrated Framework for Padding-Sink-Preserving, Alignment-Tracked Selective Cross-Attention Key–Value Cache Access in CPU-Based Whisper Speech RecognitionTechnologies · 2026
- A Cache-Aware Compression Framework: Deriving the Compression Target and Stopping Rule for Transformers on CPU-Class HardwareAI · 2026
- The Achievement of Speech Technologies in Enhancing the Rehabilitation of Hearing-Impaired PatientLecture notes in networks and systems · 2026
- Performance Evaluation of Parallel Programming Models for K-means Clustering on Parallel Computing SystemsInternational Siberian workshops and tutorials on electron devices and materials · 2026
