Recognising Covid-19 from Coughing Using Ensembles of SVMs and LSTMs with Handcrafted and Deep Audio Features.
Vincent KarasBjörn W. SchullerPublished in: Interspeech (2021)
Keyphrases
- audio features
- support vector
- audio visual
- low level
- feature set
- visual features
- music recommendation
- music information retrieval
- feature selection
- text data
- activity recognition
- knn
- sound source
- feature vectors
- machine learning
- decision trees
- multi modal
- training set
- classification accuracy
- hidden markov models
- image retrieval
- feature space
- training data
- data mining