A General Close-loop Predictive Coding Framework for Auditory Working Memory
This work addresses a gap in neural network modeling for auditory working memory, which is essential for daily activities like language acquisition, but it appears incremental as it applies an existing paradigm to a specific domain.
The authors tackled the limited modeling of auditory working memory in neural networks by proposing a general close-loop predictive coding framework, which demonstrated high semantic similarity on environmental sound and speech benchmark datasets.
Auditory working memory is essential for various daily activities, such as language acquisition, conversation. It involves the temporary storage and manipulation of information that is no longer present in the environment. While extensively studied in neuroscience and cognitive science, research on its modeling within neural networks remains limited. To address this gap, we propose a general framework based on a close-loop predictive coding paradigm to perform short auditory signal memory tasks. The framework is evaluated on two widely used benchmark datasets for environmental sound and speech, demonstrating high semantic similarity across both datasets.