Acoustic event detection based on modelling of sequence of event subparts

Abstract

The invention relates to acoustic event detection based on modeling of sequence of event subparts. Techniques are provided for acoustic event detection. A methodology implementing the techniques according to an embodiment includes extracting acoustic features from a received audio signal. The acoustic features may include, for example, one or more short-term Fourier transform frames, or other spectral energy characteristics, of the audio signal. The method also includes applying a trained classifier to the extracted acoustic features to identify and label acoustic event subparts of the audio signal and to generate scores associated with the subparts. The method further includes performing sequence decoding of the acoustic event subparts and associated scores to detect target acoustic events of interest based on the scores and temporal ordering sequence of the event subparts. The classifier is trained on acoustic event subparts that are generated through unsupervised subspace clusteringtechniques applied to training data that includes target acoustic events.

Description

technical field [0001] Embodiments herein relate generally to sound event detection based on modeling of sequences of event subparts. Background technique [0002] Acoustic event detection is playing an increasingly important role in applications related to the Internet of Things (IoT), smart home technology, and digital surveillance systems. It is often useful for the detection / recognition system to be able to respond to selected sound events of interest (eg, shots, shattering glass, crying babies, or other sounds that indicate situations that may require the attention of interested parties). Existing recognition systems generally need to be trained on sound training data sequences containing event types of interest. These events need to be labeled and their position in the data sequence must be provided, which is usually a time-consuming and expensive task. Additionally, these existing systems often cannot provide the desired level of accuracy (eg, in terms of detection ...

AI Technical Summary

Problems solved by technology

These events need to be labeled and their position in the data sequence must be provided, which is usually a time-consuming and expensive task

In addition, these existing systems often cannot provide the desired level of accuracy (e.g., in terms of detection rates and false alarm rates) necessary for some of these applications

Images