Empowering deaf-hearing communication: Exploring synergies between predictive and generative AI-based strategies towards (Portuguese) sign language interpretation

• Autor(a) principal: Adão, Telmo
• Data de Publicação: 2023
• Outros Autores: Oliveira, José A., Shahrabadi, Somayeh, Jesus, Hugo, Fernandes, Marco, Costa, Ângelo, Ferreira, Vânia, Gonçalves, Martinho Fradeira, Lopéz, Miguel A.Guevara, Peres, Emanuel, Magalhães, Luís Gonzaga Mendes
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: https://hdl.handle.net/1822/88997
• topic: Deaf-hearing communication; Generative pre-trained transformer (GPT); Inclusion; Large language models (LLM); Long-short term memory (LSTM); Machine learning (ML); Portuguese sign language; Sign language recognition (SLR); Video-based motion analytics

Communication between Deaf and hearing individuals remains a persistent challenge requiring attention to foster inclusivity. Despite notable efforts in the development of digital solutions for sign language recognition (SLR), several issues persist, such as cross-platform interoperability and strategies for tokenizing signs to enable continuous conversations and coherent sentence construction. To address such issues, this paper proposes a non-invasive Portuguese Sign Language (Língua Gestual Portuguesa or LGP) interpretation system-as-a-service, leveraging skeletal posture sequence inference powered by long-short term memory (LSTM) architectures. To address the scarcity of examples during machine learning (ML) model training, dataset augmentation strategies are explored. Additionally, a buffer-based interaction technique is introduced to facilitate LGP terms tokenization. This technique provides real-time feedback to users, allowing them to gauge the time remaining to complete a sign, which aids in the construction of grammatically coherent sentences based on inferred terms/words. To support human-like conditioning rules for interpretation, a large language model (LLM) service is integrated. Experiments reveal that LSTM-based neural networks, trained with 50 LGP terms and subjected to data augmentation, achieved accuracy levels ranging from 80% to 95.6%. Users unanimously reported a high level of intuition when using the buffer-based interaction strategy for terms/words tokenization. Furthermore, tests with an LLM—specifically ChatGPT—demonstrated promising semantic correlation rates in generated sentences, comparable to expected sentences.