Timezone: »
Adaptive Front-ends for End-to-end Source Separation
Shrikant Venkataramani · Paris Smaragdis
Fri Dec 08 09:25 AM -- 09:45 AM (PST) @ None
Event URL: http://media.aau.dk/smc/wp-content/uploads/2017/12/ML4AudioNIPS17_paper_39.pdf »
(+ Jonah Casebeer) 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. We present an auto-encoder neural network that can act as an equivalent to short-time front-end transforms. We demonstrate the ability of the network to learn optimal, real-valued basis functions directly from the raw waveform of a signal and further show how it can be used as an adaptive front-end for end-to-end supervised source separation.
Author Information
Shrikant Venkataramani (University of Illinois at Urbana Champaign)
Paris Smaragdis (University of Illinois Urbana-Champaign)
More from the Same Authors
-
2017 : Poster Session Speech: source separation, enhancement, recognition, synthesis »
Shuayb Zarar · Rasool Fakoor · SRI HARSHA DUMPALA · Minje Kim · Paris Smaragdis · Mohit Dubey · Jong Hwan Ko · Sakriani Sakti · Yuxuan Wang · Lijiang Guo · Garrett T Kenyon · Andros Tjandra · Tycho Tax · Younggun Lee -
2014 Poster: Spectral Learning of Mixture of Hidden Markov Models »
Cem Subakan · Johannes Traa · Paris Smaragdis -
2009 Poster: A Sparse Non-Parametric Approach for Single Channel Separation of Known Sounds »
Paris Smaragdis · Madhusudana Shashanka · Bhiksha Raj -
2007 Poster: Sparse Overcomplete Latent Variable Decomposition of Counts Data »
Madhusudana Shashanka · Bhiksha Raj · Paris Smaragdis