Audiovisual speech recognition based on a deep convolutional neural network

Audiovisual speech recognition based on a deep convolutional neural network

Audiovisual speech recognition is an emerging research topic. Lipreading is the recognition of what someone is saying using visual information, primarily lip movements. In this study, we created a custom dataset for Indian English linguistics and categorized it into three main categories: (1) audio...

Cur síos iomlán

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí: Shashidhar Rudregowda, Sudarshan Patilkulkarni, Vinayakumar Ravi, Gururaj H.L., Moez Krichen
Formáid: Alt
Teanga:English
Foilsithe / Cruthaithe: KeAi Communications Co. Ltd. 2024-03-01
Sraith:Data Science and Management
Ábhair:
Audiovisual speech recognition
Custom dataset
1D Convolution neural network (CNN)
Deep CNN (DCNN)
Long short-term memory (LSTM)
Lipreading
Rochtain ar líne:http://www.sciencedirect.com/science/article/pii/S2666764923000450

Ar líne

http://www.sciencedirect.com/science/article/pii/S2666764923000450

Míreanna comhchosúla