arXiv (Cornell University) · 2017 · 31 citations · 16 references
ComputingComputer ScienceAcousticsComputer VisionMachine LearningAuditory Scene AnalysisDeep LearningMulti-task LearningRepresentation LearningSpeech RecognitionConvolutional Neural NetworksDeep Learning-based DetectionDevelopment DataImbalanced ClassificationImbalanced LearningMulti-task Deep LearningMulti-task OptimizationMulti-task Regularization
This report presents our audio event detection system submitted for Task 2, "Detection of rare sound events", of DCASE 2017 challenge. The proposed system is based on convolutional neural networks (CNNs) and deep neural networks (DNNs) coupled with novel weighted and multi-task loss functions and state-of-the-art phase-aware signal enhancement. The loss functions are tailored for audio event detection in audio streams. The weighted loss is designed to tackle the common issue of imbalanced data in background/foreground classification while the multi-task loss enables the networks to simultaneously model the class distribution and the temporal structures of the target events for recognition. Our proposed systems significantly outperform the challenge baseline, improving F-score from 72.7% to 90.0% and reducing detection error rate from 0.53 to 0.18 on average on the development data. On the evaluation data, our submission obtains an average F1-score of 88.3% and an error rate of 0.22 which are significantly better than those obtained by the DCASE baseline (i.e. an F1-score of 64.1% and an error rate of 0.64).
16
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Metrics for Polyphonic Sound Event Detection
Annamaria Mesaros, Toni Heittola, Tuomas Virtanen · Applied Sciences · 2016 · 572 citations · Full text
Vocal Tract Length Perturbation (VTLP) improves speech recognition
Navdeep Jaitly, Ella Hinton · 2013 · 335 citations