Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/88997
Título: | Empowering deaf-hearing communication: Exploring synergies between predictive and generative AI-based strategies towards (Portuguese) sign language interpretation |
Autor(es): | Adão, Telmo 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 |
Palavras-chave: | 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 |
Data: | 1-Nov-2023 |
Editora: | MDPI |
Revista: | Journal of Imaging |
Resumo(s): | 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. |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/88997 |
DOI: | 10.3390/jimaging9110235 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | CAlg - Artigos em revistas internacionais / Papers in international journals |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
jimaging-09-00235-v2 (1).pdf | 7,02 MB | Adobe PDF | Ver/Abrir |