Back to Search
Start Over
Continuous robust sound event classification using time-frequency features and deep learning
- Source :
- PLoS ONE, PLoS ONE, Vol 12, Iss 9, p e0182309 (2017)
- Publication Year :
- 2017
- Publisher :
- Public Library of Science (PLoS), 2017.
-
Abstract
- The automatic detection and recognition of sound events by computers is a requirement for a number of emerging sensing and human computer interaction technologies. Recent advances in this field have been achieved by machine learning classifiers working in conjunction with time-frequency feature representations. This combination has achieved excellent accuracy for classification of discrete sounds. The ability to recognise sounds under real-world noisy conditions, called robust sound event classification, is an especially challenging task that has attracted recent research attention. Another aspect of real-word conditions is the classification of continuous, occluded or overlapping sounds, rather than classification of short isolated sound recordings. This paper addresses the classification of noise-corrupted, occluded, overlapped, continuous sound recordings. It first proposes a standard evaluation task for such sounds based upon a common existing method for evaluating isolated sound classification. It then benchmarks several high performing isolated sound classifiers to operate with continuous sound data by incorporating an energy-based event detection front end. Results are reported for each tested system using the new task, to provide the first analysis of their performance for continuous sound event detection. In addition it proposes and evaluates a novel Bayesian-inspired front end for the segmentation and detection of continuous sound recordings prior to classification.
- Subjects :
- Computer science
Speech recognition
Markov models
lcsh:Medicine
Social Sciences
Otology
02 engineering and technology
Field (computer science)
Machine Learning
Mathematical and Statistical Techniques
Hearing
Medicine and Health Sciences
0202 electrical engineering, electronic engineering, information engineering
Feature (machine learning)
Psychology
Hidden Markov models
lcsh:Science
Hidden Markov model
Sound (geography)
Multidisciplinary
geography.geographical_feature_category
Event (computing)
Physics
Audiology
Sound
Background Noise (Acoustics)
Physical Sciences
Engineering and Technology
Sensory Perception
0305 other medical science
Algorithms
Research Article
Computer and Information Sciences
Ambient noise level
Research and Analysis Methods
030507 speech-language pathology & audiology
03 medical and health sciences
Humans
geography
Computers
business.industry
Deep learning
lcsh:R
Biology and Life Sciences
Probability theory
020206 networking & telecommunications
Acoustics
Models, Theoretical
Convolution
Otorhinolaryngology
Speech Signal Processing
Signal Processing
lcsh:Q
Artificial intelligence
business
Mathematical Functions
Mathematics
Neuroscience
Subjects
Details
- ISSN :
- 19326203
- Volume :
- 12
- Database :
- OpenAIRE
- Journal :
- PLOS ONE
- Accession number :
- edsair.doi.dedup.....3b4d2d00838fec0b84b447f8f48f80e3