Music data processing method and device

• Main Authors: PAN LI, LI XINZHU, HAO RUNHUA, WANG HERAN, TIAN YE
• Format: Patent
• Language: Chinese; English
• Published: 12.01.2024
• Subjects: ACOUSTICS; CALCULATING; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; MUSICAL INSTRUMENTS; PHYSICS; PICTORIAL COMMUNICATION, e.g. TELEVISION; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The invention relates to the field of music audio processing, in particular to a music data processing method and device, and the method comprises the steps: constructing emotion tags of a plurality of pieces of target music in advance; then constructing a dichotomy model corresponding to each emotion label, classifying the target music based on the dichotomy model corresponding to each emotion label, and when the number of the plurality of emotion labels obtained by the target music exceeds a first threshold value, extracting classification probability distribution of each emotion label of the target music; normalizing the classification probability distribution of each emotion label of the target music to form a multi-dimensional classification vector, distributing a corresponding space coordinate position to the multi-dimensional classification vector, and storing the space coordinate position corresponding to the multi-dimensional classification vector to form a space data set; and classifying the target