Sound identification method based on cross acoustic array broadband wave beam formation

Abstract

The invention discloses a sound identification method based on a cross acoustic array broadband wave beam formation. The sound identification method comprises steps of using a cross acoustic array to align with a needed direction to collect acoustic signals, 2, performing pre-processing on collected sound, 3, performing DFT (discrete Fourier transform) on processed data of each frame, performing frequency band extraction according to a needed frequency band, 4, performing LSMI-MVDR wave beam formation on the needed direction by the extracted frequency band, 5, performing inverse DFT on a frequency domain signal after the wave beam is formed, 6, performing frame overlapping synthesis according to the framing principle to output a signal, and 7, performing characteristic extraction and classification study and identification. The sound identification method based on cross acoustic array broadband wave beam formation can improve a signal-to-noise ratio of the signal received in an expected direction, inhibits interference signals of other directions, can be applied to a signal processing process of an acoustic identification system and can effectively improve an identification rate and reliability of the identification system on the identification object.

Description

technical field [0001] The invention belongs to the technical field of signal processing, and in particular relates to an acoustic recognition method based on broadband beamforming of a cross-shaped acoustic array. Background technique [0002] In the traditional single-microphone sound recognition system, there are several problems as follows: [0003] 1. The sound recognition system only needs to recognize signals in a certain direction. However, due to the omnidirectionality of a single microphone, when the recognition object is not near the direction, the recognition system will still be triggered, resulting in false alarms. [0004] 2. In a real complex environment, there are many kinds of interference sound sources and serious background noise near the recognition object, which will cause the overall recognition rate of the system to drop sharply, and the false alarm rate and missed alarm rate will rise sharply. [0005] 3. In practical applications, in order to incre...

AI Technical Summary

Problems solved by technology

[0003] 1. The sound recognition system only needs to recognize signals in a certain direction. However, due to the omnidirectionality of a single microphone, when the recognition object is not near the direction, the recognition system will still be triggered, resulting in false alarms

[0004] 2. In the real complex environment, there are many kinds of interference sound sources and serious background noise near the recognition object, which will cause the overall recognition rate of the system to drop sharply, and the false alarm rate and missed alarm rate will rise sharply

[0005] 3. In practical applications, in order to increase the limit distance of the recognition system's action area, a high-sensitivity microphone will be used. However, a high-sensitivity microphone will inevitably lead to an increase in background noise, resulting in a low recognition rate for long distances. There is a significant increase, but it will decrease

Images