Enhancing LSTM RNN-Based Speech Overlap Detection by Artificially Mixed Data.
Gerhard HagererVedhas PanditFlorian EybenBjörn W. SchullerPublished in: Semantic Audio (2017)
Keyphrases
- mixed data
- recurrent neural networks
- detection algorithm
- object detection
- nearest neighbor
- noisy environments
- detection rate
- false positives
- long short term memory
- detection accuracy
- data compression
- speech recognition
- decision trees
- knn
- similarity function
- false alarms
- data sets
- back propagation
- automatic detection
- feed forward
- mixture of gaussian distributions
- anomaly detection
- pairwise
- feature space
- automatic speech recognition
- clustering algorithm
- neural network