Fault detection method and device for voiceprint acquisition device based on deep learning

• Main Authors: TAO HUIFANG, CHEN ZHUONAN, CAO ZUYANG, ZHANG KAIQIANG, BAO JUNJIAN, ZHANG YONGQUAN, FANG JI
• Format: Patent
• Language: Chinese; English
• Published: 10.01.2023
• Subjects: ACOUSTICS; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The embodiment of the invention provides a fault detection method and device for a voiceprint collection device based on deep learning, and the method comprises the steps: carrying out the permutation and combination of the fault types of the voiceprint collection device, obtaining fault voiceprint information and normal voiceprint information, carrying out the preprocessing, obtaining corresponding normal frequency domain features and fault frequency domain features, and carrying out the detection of the fault types of the voiceprint collection device. And inputting the normal frequency domain feature, the fault frequency domain feature and the fault type into a convolutional neural network model for training, outputting the operation voiceprint information of the target equipment to the convolutional neural network model, and judging whether the target equipment has a fault or not and the fault type according to the output fault type data. By adopting the method, whether the voiceprint acquisition device ha