Intelligent Background Sound Event Detection and Classification based on WOLA Spectral Analysis in Hearing Devices

Abstract

Audio signals from real-life hearing devices typically contain background noises. The purpose of this thesis is to build a system model which can automatically separate background noise from noisy speech, and then classify background sound into predefined event categories. This thesis proposed to use weighted overlap-add algorithm (WOLA) for feature extraction and neural network (NN) for sound event detection. In this approach, an energy waveform ‘trough detection’ algorithm is used to separate out speech gaps which primarily contain background noise. To further analyze the noise signal’s spectrum, the WOLA algorithm is used to extract spectral features by transforming a fraction of time domain signal into frequency domain data represented in 22 channels. Moreover, a feed-forward neural network with one hidden layer is used to recognize each event’s diverse spectral feature pattern. Then it produces classification decisions based on confidence values. Recordings of 11 realistic background noise scenes, mixed with human speech at Signal to Noise Ratio (SNR) of 5 dB, are used for training. NN will learn the mapping between spectral feature characteristics and sound events categories. After training, the neural network classifier is evaluated by measuring the accuracy of event classification. The overall detection accuracy has achieved 96%, while the event ‘hallway’ has the lowest detection rate at 85%. This detection algorithm has the ability to improve noise reduction in hearing devices by applying distinct compensation gains, which attenuate the noise dominated frequency bands for each particular predefined event. In our preliminary evaluation experiment, the application of gain patterns has been proven to be effective in reducing background noise. Its combinational usage with instant gain pattern would produce improved results with noticeably attenuated noise and smooth spectral cues in the processed audio output.