most citedDeep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network

15 citations · 66 across the 9 of their papers we have counts for

collaborators

9 papers

cs.SD20155 cited

Time-Frequency Trade-offs for Audio Source Separation with Binary Masks

Andrew J. R. Simpson

The short-time Fourier transform (STFT) provides the foundation of binary-mask based audio source separation approaches. In computing a spectrogram, the STFT window size parameteri…

cs.SD201515 cited

Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network

Andrew J. R. Simpson, Gerard Roma, Mark D. Plumbley

Identification and extraction of singing voice from within musical mixtures is a key challenge in source separation and machine audition. Recently, deep neural networks (DNN) have…

cs.SD20154 cited

Deep Transform: Cocktail Party Source Separation via Complex Convolution in a Deep Neural Network

Andrew J. R. Simpson

Convolutional deep neural networks (DNN) are state of the art in many engineering problems but have not yet addressed the issue of how to deal with complex spectrograms. Here, we u…

cs.SD201515 cited

Probabilistic Binary-Mask Cocktail-Party Source Separation in a Convolutional Deep Neural Network

Andrew J. R. Simpson

Separation of competing speech is a key challenge in signal processing and a feat routinely performed by the human auditory brain. A long standing benchmark of the spectrogram appr…

cs.SD20153 cited

Deep Transform: Cocktail Party Source Separation via Probabilistic Re-Synthesis

Andrew J. R. Simpson

In cocktail party listening scenarios, the human brain is able to separate competing speech signals. However, the signal processing implemented by the brain to perform cocktail par…

cs.SD2015

Deep Transform: Time-Domain Audio Error Correction via Probabilistic Re-Synthesis

Andrew J. R. Simpson

In the process of recording, storage and transmission of time-domain audio signals, errors may be introduced that are difficult to correct in an unsupervised way. Here, we train a…