Context-dependent sound event detection

Annamaria Mesaros,Tuomas Virtanen,Antti Eronen,Toni Heittola

doi:10.1186/1687-4722-2013-1

Annamaria Mesaros, Tuomas Virtanen + Show 2 more

Open Access

https://doi.org/10.1186/1687-4722-2013-1

Copy DOI

Abstract

The work presented in this article studies how the context information can be used in the automatic sound event detection process, and how the detection system can benefit from such information. Humans are using context information to make more accurate predictions about the sound events and ruling out unlikely events given the context. We propose a similar utilization of context information in the automatic sound event detection process. The proposed approach is composed of two stages: automatic context recognition stage and sound event detection stage. Contexts are modeled using Gaussian mixture models and sound events are modeled using three-state left-to-right hidden Markov models. In the first stage, audio context of the tested signal is recognized. Based on the recognized context, a context-specific set of sound event classes is selected for the sound event detection stage. The event detection stage also uses context-dependent acoustic models and count-based event priors. Two alternative event detection approaches are studied. In the first one, a monophonic event sequence is outputted by detecting the most prominent sound event at each time instance using Viterbi decoding. The second approach introduces a new method for producing polyphonic event sequence by detecting multiple overlapping sound events using multiple restricted Viterbi passes. A new metric is introduced to evaluate the sound event detection performance with various level of polyphony. This combines the detection accuracy and coarse time-resolution error into one metric, making the comparison of the performance of detection algorithms simpler. The two-step approach was found to improve the results substantially compared to the context-independent baseline system. In the block-level, the detection accuracy can be almost doubled by using the proposed context-dependent event detection.

Highlights

Sound events are good descriptors for an auditory scene, as they help describing and understanding the human and social activities
The best performing system submitted to the evaluation achieved a 30% detection accuracy by using AdaBoost-based feature selection and a Hidden Markov Model (HMM) classifier [25]
The proposed approach utilizing the context information comprised a context recognition stage and a sound event detection stage using the information of the recognized context

Summary

Introduction

Sound events are good descriptors for an auditory scene, as they help describing and understanding the human and social activities. A sound event is a label that people would use to describe a recognizable event in a region of the sound. Such a label usually allows people to understand the concept behind it and associate this event with other known events. Sound events can be used to represent a scene in a symbolic way, e.g., an auditory scene on a busy street contains events of passing cars, car horns, and footsteps of people rushing. Auditory scenes can be described with different level descriptors to represent the general context (street) and the characteristic sound events (car, car horn, and footsteps). The definition of context is narrowed to the location of auditory scene

Objectives

Discussion

Conclusion