Voice signal processing method and device

• Main Authors: YU LIBIAO, ZHANG JING
• Format: Patent
• Language: Chinese; English
• Published: 22.10.2019
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The invention discloses a voice signal processing method and device, and relates to the technical field of voice. The specific implementation scheme is as follows: terminal equipment performs spatialfiltering on the acquired n paths of omni-directional microphone array signals by using a spatial filtering coefficient of m sound zones to generate m paths of enhanced signals, wherein m and n are positive integers; pre-enhancement processing is carried out on the m paths of enhanced signals by the terminal equipment respectively, wherein the pre-enhancement processing comprises echo cancellationand noise estimation to obtain m paths of signals after pre-enhancement processing; one path of signals with the highest energy and the highest signal-to-noise ratio is selected from the m paths of signals after pre-enhancement processing by the terminal equipment, and noise suppression and automatic gain control are carried out on the selected one path of the signals to generate the processed voice signal. Therefore, a v