Audio watermark processing method and device, computer equipment and storage medium

• Main Authors: CHANG QINWEI, YANG TIANSHU, LIU SHAOTENG, HUANG LEICHAO, LIU HUALUO
• Format: Patent
• Language: Chinese; English
• Published: 13.01.2023
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The invention relates to an audio watermark processing method and device, computer equipment and a storage medium. The method comprises the following steps: dividing an audio to be processed to obtain a plurality of audio clips, and determining an original frequency domain coefficient corresponding to each audio clip; to-be-embedded information is obtained, the to-be-embedded information comprises mark information and watermark information, and the mark information is used for achieving positioning of the watermark information; determining an adjustment amount of an original frequency domain coefficient corresponding to each audio clip based on the to-be-embedded information; performing inverse frequency domain transformation on the adjustment amount corresponding to each audio clip to obtain a to-be-superposed clip corresponding to each audio clip; and superposing each audio clip with the corresponding to-be-superposed clip to obtain a plurality of target audio clips, and obtaining a target audio embedded wi