Abstract: A deep neural network can be trained to output motion or deformation information for a character that is representative of the character uttering speech contained in audio input, which is accurate for an emotional state of the character. The character can have different facial components or regions (e.g., head, skin, eyes, tongue) modeled separately, such that the network can output motion or deformation information for each of these different facial components. During training, the network can be provided with emotion and/or style vectors that indicate information to be used in generating realistic animation for input speech, as may relate to one or more emotions to be exhibited by the character, a relative weighting of those emotions, and any style or adjustments to be made to how the character expresses that emotional state. The network output can be provided to a renderer to generate audio-driven facial animation that is emotion-accurate.

Abstract: A method and a system for controlling quality of service of a storage system, and a storage system. The method includes: collecting information about processing capabilities of the hard disks in the storage system and obtaining processing capabilities of the hard disks according to the information about processing capabilities; dividing a cache into multiple cache tiers according to the processing capabilities of the hard disks; and writing, for a cache tier in which dirty data reaches a preset threshold, data in the cache tier into at least one hard disk corresponding to the cache tier. The method avoids a phenomenon of preempting page resources in the cache.

Abstract: A method and a system for controlling quality of service of a storage system, and a storage system. The method includes: collecting information about processing capabilities of the hard disks in the storage system and obtaining processing capabilities of the hard disks according to the information about processing capabilities; dividing a cache into multiple cache tiers according to the processing capabilities of the hard disks; and writing, for a cache tier in which dirty data reaches a preset threshold, data in the cache tier into at least one hard disk corresponding to the cache tier. The method avoids a phenomenon of preempting page resources in the cache.