Piano audio data processing method and device, electronic equipment and storage medium

• Main Authors: RU GANGHUI, CHENG NING, WANG JIANZONG, ZHANG XULONG
• Format: Patent
• Language: Chinese; English
• Published: 08.08.2023
• Subjects: ACOUSTICS; 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 piano audio data processing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: segmenting a target piano spectrum according to a preset frame length to obtain original spectrum slices; performing embedding representation on the original frequency spectrum slice to obtain a frequency spectrum slice embedding vector, and performing position coding on the original frequency spectrum slice to obtain a frequency spectrum slice position vector; carrying out vector addition on the frequency spectrum slice embedding vector and the frequency spectrum slice position vector to obtain a frequency spectrum slice target representation vector; combining the spectrum slice target representation vectors to obtain a spectrum vector sequence; inputting the spectrum vector sequence into a preset attention model for sequence feature extraction to obtain a note context vecto