3 results about "False awakening" patented technology

The invention discloses a wake-up processing method and device based on far-field voice, and terminal equipment, and relates to the technical field of voice recognition wake-up, and the method comprises the steps: carrying out the analysis processing of a detected wake-up audio, and calculating a wake-up confidence score; when the calculated wake-up confidence score of the wake-up audio is greater than or equal to a preset threshold value, determining that the wake-up is effective and controlling to enter a normal voice interaction process; when the calculated wake-up confidence score of the wake-up audio is lower than a preset threshold value, sending the wake-up audio to a background for voice recognition; performing second-level judgment: judging whether the character information of the voice recognition is consistent with a preset wake-up word or not; if so, entering a normal voice interaction process; and if not, false wake-up is confirmed, and the voice interaction process is controlled to be ended. According to the invention, the false awakening condition caused by environmental noise, similar pronunciation and the like can be solved, and convenience is provided for the use of a user.

This invention provides a method and system for sleep stage detection and intervention based on cardiac impulse signals, belonging to the field of sleep monitoring. The method includes: acquiring sleep cardiac impulse signals and separating them into multiple modal physiological signal sequences; extracting feature vectors from each sequence and calculating attention weights using modal correlation; weighted fusion to generate a multimodal fusion feature vector and determining the current sleep stage; outputting acoustic stimulation signals when in slow-wave sleep, and monitoring changes in cardiac impulse signals in real time during the output process, adjusting the stimulation if body movement exceeds limits or sleep becomes shallow. This application achieves dynamic weighted fusion of multimodal features through a self-attention mechanism, solving the problem of single signals being easily interfered with in non-contact monitoring, and significantly improving the accuracy of sleep staging; by sending adjustment commands when body movement intensity exceeds limits or sleep becomes shallow, the acoustic stimulation is adjusted, effectively avoiding false awakenings while enhancing slow-wave sleep, ensuring the safety and effectiveness of sleep intervention.

The invention discloses a voice detection method, device and equipment, a medium and a product. The method comprises the following steps: recognizing voice text information in interactive voice; determining a wake-up word in the voice text information and a pre-wake-up text associated with the wake-up word; and determining a wake-up response condition of the vehicle interaction equipment according to the attribute information of the pre-wake-up text. According to the invention, the voice text information in the interaction voice is identified, the wake-up word and the pre-wake-up text associated with the wake-up word are identified and extracted from the voice text information, and whether to wake up the vehicle interaction device is determined based on the attribute information of the pre-wake-up text. The situation that the vehicle interaction device can be awakened by referring to the awakening word in a normal conversation is avoided, so that the false awakening rate of the vehicle interaction device is reduced, and the use experience of a user is improved.