This paper introduces the concept of an intelligent vase that combines the cultivation of plants with psychotherapy for the Alzheimer’s adjuvant therapy (from now on, referred to as AD) of patients. RECALL (The name of intelligent vase which defined by this paper), which includes hardware and software applications, as well as a unique hand gesture interaction method, is able to collect patients’ hand gestures and play photos, to remind patients of the plant’s growth status. To evaluate our conceptual system, we created a preliminary prototype. We conducted an experiment with leap motion. This project tries to explore a kind of interaction method by cultivating plants to simulate cognitive training activities, to stimulate memories through family pictures, to slow down the cognitive decline from AD, to incorporate non-drug intervention into the family life of AD patients, to reduce the expenditure, time, and energy costs, and to improve the quality of life of patients and their families.

This research aims to explore the integration method of deep learning and large language models in speech recognition to improve the system’s recognition accuracy and ability to handle complex contexts. Deep neural network (DNN), convolutional neural network (CNN), long short-term memory network (LSTM) and Transformer-based large language model are used to build an integrated acoustic and language model framework. Experiments on TIMIT, LibriSpeech and Common Voice datasets show that the ensemble model shows significant improvements in both word error rate (WER) and real-time factor (RTF) compared to traditional models. Especially in terms of adaptability to multiple languages and accent changes, the model shows superior performance. The conclusion shows that through technology integration, the performance of the speech recognition system in complex environments can be effectively improved, providing a new direction for the future development of speech recognition technology.