Timezone: »

Adaptive Front-ends for End-to-end Source Separation
Shrikant Venkataramani · Paris Smaragdis

Fri Dec 08 09:25 AM -- 09:45 AM (PST) @
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