Abstract: Provided are a water outlet device (1) and an intelligent closestool. The water outlet device (1) includes a core (100). The core (100) includes a mixing chamber (110), one or more first water inlets (120), one or more second water inlets (130), and a water outlet (140). The water outlet (140) connects with the mixing chamber (110). A tangential direction, a radial direction, and an axial direction of the mixing chamber (110) are defined. The one or more first water inlets (120) are disposed in the mixing chamber (110) along the tangential direction so that a water flow entering the mixing chamber (110) from the one or more first water inlets (120) is capable of forming a vortex. The one or more second water inlets (130) are disposed in the mixing chamber (110) along the axial direction or the radial direction so that a water flow entering the mixing chamber (110) from the one or more second water inlets (130) is capable of forming a stable water flow.

Abstract: The present disclosure provides a weakly-supervised sound event detection method and system based on adaptive hierarchical pooling. The system includes an acoustic model and an adaptive hierarchical pooling algorithm module (AHPA-model), where the acoustic model inputs a pre-processed and feature-extracted audio signal, and predicts a frame-level prediction probability aggregated by the AHPA-module to obtain a sentence-level prediction probability. The acoustic model and a relaxation parameter are jointly optimized to obtain an optimal model weight and an optimal relaxation parameter based for formulating each category of sound event. A pre-processed and feature-extracted unknown audio signal is input to obtain frame-level prediction probabilities of all target sound events (TSEs), and sentence-level prediction probabilities of all categories of TSEs are obtained based on an optimal pooling strategy of each category of TSE.