Audio analysis method and device, equipment and storage medium

• Main Authors: ZHANG CHEN, ZHENG XIGUANG, WEI YAODU
• Format: Patent
• Language: Chinese; English
• Published: 16.05.2023
• 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 analysis method and device, equipment and a storage medium, relates to the technical field of computers, and is used for solving the problems of relatively low accuracy and relatively high cost when audio data of a terminal is processed in a general technology. The audio analysis method comprises the following steps: acquiring dry audio data of a target audio; inputting the dry sound audio data into a target phoneme recognition model for phoneme recognition processing to obtain a target phoneme time sequence; the target phoneme recognition model is obtained by training a phoneme set after homophonic combination based on a plurality of languages; inputting the dry sound audio data into a target text recognition model for text recognition processing to obtain a target text time sequence; the target text recognition model is obtained by training lyric information based on the target audio; determining audio signal feature information of the dry sound audio data; and according to