Knock-Knock: Acoustic Object Recognition by using Stacked Denoising Autoencoders

TL;DR

This paper demonstrates that deep learning with stacked denoising autoencoders significantly improves acoustic object recognition accuracy and speed compared to traditional handcrafted feature methods.

Contribution

The study introduces a deep learning approach using stacked denoising autoencoders for acoustic object recognition, eliminating the need for handcrafted features and achieving higher accuracy and efficiency.

Findings

Achieved 91.50% recognition accuracy with deep learning.

Deep learning classification is over 6 times faster than traditional methods.

Traditional handcrafted features yielded only 58.22% accuracy.

Abstract

This paper presents a successful application of deep learning for object recognition based on acoustic data. The shortcomings of previously employed approaches where handcrafted features describing the acoustic data are being used, include limiting the capability of the found representation to be widely applicable and facing the risk of capturing only insignificant characteristics for a task. In contrast, there is no need to define the feature representation format when using multilayer/deep learning architecture methods: features can be learned from raw sensor data without defining discriminative characteristics a-priori. In this paper, stacked denoising autoencoders are applied to train a deep learning model. Knocking each object in our test set 120 times with a marker pen to obtain the auditory data, thirty different objects were successfully classified in our experiment and each object was knocked 120 times by a marker pen to obtain the auditory data. By employing the proposed deep learning framework, a high accuracy of 91.50% was achieved. A traditional method using handcrafted features with a shallow classifier was taken as a benchmark and the attained recognition rate was only 58.22%. Interestingly, a recognition rate of 82.00% was achieved when using a shallow classifier with raw acoustic data as input. In addition, we could show that the time taken to classify one object using deep learning was far less (by a factor of more than 6) than utilizing the traditional method. It was also explored how different model parameters in our deep architecture affect the recognition performance.