Reverberation voice processing method and device, electronic equipment and storage medium

• Main Authors: QING RUI, YU LIBIAO, WEI JIANQIANG, ZHANG GUOCHANG
• Format: Patent
• Language: Chinese; English
• Published: 08.04.2022
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The invention provides a reverberation voice processing method and device, electronic equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as voice technology and deep learning. Comprising the steps of obtaining original voice data; delaying the original voice data to generate first reference voice data; performing sub-band decomposition on the original voice data and the first reference voice data to obtain a first complex signal, a first amplitude spectrum and a first phase spectrum corresponding to the original voice data and a second complex signal corresponding to the first reference voice data; determining a first amplitude mask corresponding to the original voice data according to the first complex signal and the second complex signal; and performing sub-band synthesis on the first amplitude mask, the first amplitude spectrum and the first phase spectrum to obtain reverberation-removed voice data. Therefore