Speech enhancement network training method and device, speech enhancement method and device and electronic equipment

• Main Authors: ZHANG CHEN, CHEN LIANWU, ZHENG XIGUANG
• Format: Patent
• Language: Chinese; English
• Published: 20.01.2023
• 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 a voice enhancement network training method and device, a voice enhancement method and device and electronic equipment. The method comprises the steps that sample voice information, a pure voice signal, an original impact response signal, first equipment frequency response and target sound source distribution data corresponding to target sound source characteristics are acquired; performing sound source separation processing on the original impact response signal to obtain an original direct source response signal and an original reflection source response signal; performing sound source characteristic alignment processing based on the target sound source distribution data, the original direct source response signal and the original reflection source response signal to obtain a target impact response signal; generating target enhanced voice information corresponding to the sample voice information based on the target impact response signal, the pure voice signal and the first equipmen