479 citations · 1.5k across the 53 of their papers we have counts for
5 papers · 1 filter
Generative Adversarial Source Separation
Cem Subakan, Paris Smaragdis
Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversari…
Neural Network Alternatives to Convolutive Audio Models for Source Separation
Shrikant Venkataramani, Y. Cem Subakan, Paris Smaragdis
Convolutive Non-Negative Matrix Factorization model factorizes a given audio spectrogram using frequency templates with a temporal dimension. In this paper, we present a convolutio…
Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization
Nasser Mohammadiha, Paris Smaragdis, Arne Leijon
Reducing the interference noise in a monaural noisy speech signal has been a challenging task for many years. Compared to traditional unsupervised speech enhancement methods, e.g.,…
End-to-end Source Separation with Adaptive Front-Ends
Shrikant Venkataramani, Jonah Casebeer, Paris Smaragdis
Source separation and other audio applications have traditionally relied on the use of short-time Fourier transforms as a front-end frequency domain representation step. The unavai…
Diagonal RNNs in Symbolic Music Modeling
Y. Cem Subakan, Paris Smaragdis
In this paper, we propose a new Recurrent Neural Network (RNN) architecture. The novelty is simple: We use diagonal recurrent matrices instead of full. This results in better test…