期刊论文

Chen, Aibin

英文

Ecological Informatics

1574-9541

2019

54

101009

10.1016/j.ecoinf.2019.101009

The audio of bird sound used in this research was acquired from the xeno-canto website using an automatic script. The audio file is in MP3 format, with sampling frequency of 48,000 Hz, and bit rate of 320,000 bps. The duration of each audio file varies. Since all the audio data of the website are uploaded by volunteers from all over the world and recorded in the natural environment, there inevitably be the alternating and overlapping case of background noise and bird sound in the audio data.

本校为第一且通讯机构

Inspired by that bird sound has various frequency distributions and continuous time-varying properties, a novel method is proposed for the classification of bird sound based on continuous frame sequence and spectrogram-frame linear network (SFLN). In order to form a continuous frame sequence as the standard input for SFLN, a sliding window algorithm of short frame length is suitable for differentiate the Mel-spectrogram of bird sound. The vertical 3D filter in the linear layer moves linearly along the continuous frame and cover its full frequency band. The weight is initialized to a Gaussian d...