Lexical Acquisition from Audio-Visual Streams Using a Multimodal Recurrent State-Space Model
Conference proceeding (November 2023)
The most recent citing publications are shown below. View all 6 publications that cite this research output on Dimensions.
Unsupervised phoneme and word acquisition from continuous speech based on a hierarchical probabilistic generative model
Article in Advanced Robotics (September 2023)
Unsupervised Multimodal Word Discovery Based on Double Articulation Analysis With Co-Occurrence Cues
Article in IEEE Transactions on Cognitive and Developmental Systems (August 2023)