An emotion monitoring system and method based on intelligent safety helmet voice perception

By using the voice perception system of the smart safety helmet, audio and visual features are extracted and fused, and noise is separated using an improved U-net model to generate clean voice features and convert them into text sequences. This solves the problem of accuracy in emotion recognition at construction sites and enables digital management and safety control of construction sites.

CN122337259APending Publication Date: 2026-07-03HUAFENG TECH (NANJING) CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202610496851.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-15
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

When construction workers wear masks, their facial expressions are obscured. Existing emotion recognition methods lack effective references for facial expressions and rely solely on tone of voice to determine emotions, making it difficult to accurately capture true emotional states. This results in a lack of accurate basis for safety management at construction sites, and traditional management models are inefficient, subjective, and information-lagging.

Method used

By using a voice perception system based on a smart safety helmet, audio and visual features from the construction site are extracted, fused into multimodal features, and noise is separated using an improved U-net model to generate clean speech features and convert them into text sequences. Combined with video streams, emotion recognition is performed to generate digital profiles with emotion tags.

Benefits of technology

It achieves efficient recognition of construction workers' emotions in complex noise environments, improves the accuracy of speech separation and work content extraction, adapts to mask-wearing scenarios, solves the emotion recognition bias caused by the lack of facial expressions, and realizes digital management and safety control of construction sites.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122337259A_ABST
    Figure CN122337259A_ABST
Patent Text Reader

Abstract

This invention discloses an emotion monitoring system and method based on voice perception of smart safety helmets, belonging to the technical field of speech processing. The system acquires video streams from a construction site and extracts audio and visual features. These features are then fused to obtain multimodal features, which are input into an improved model to obtain a binary spectral mask. The binary spectral mask is combined with the audio features and subjected to time-frequency domain transformation to obtain clean speech features. A text sequence is generated based on these clean speech features. The clean speech features, text sequence, and video stream are input into a target model to obtain emotion tags. Work logs are retrieved, and emotion tags are added to the work logs to obtain digital archives. By fusing audio and visual features from the construction video stream, the improved model achieves speech separation under complex noise conditions, extracts work content, generates text, and accurately identifies the emotions of mask-wearing workers by combining multi-dimensional information, generating digital archives with emotion tags.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Voice emotion recognition method based on multiple scales and multiple features

    CN121214975A