An Efficient Time-Frequency Method for Synthesizing Noisy Sounds With Short Transients and Narrow Spectral Components.
Damián MarelliMitsuko AramakiRichard Kronland-MartinetCharles VerronPublished in: IEEE Trans. Speech Audio Process. (2012)
Keyphrases
- high accuracy
- cost function
- experimental evaluation
- synthetic data
- dynamic programming
- computational cost
- classification method
- detection method
- clustering method
- computationally efficient
- probabilistic model
- neural network
- significant improvement
- preprocessing
- objective function
- segmentation method
- image processing