AI News, Deep Learning Machine Solves the Cocktail Party Problem

Deep Learning Machine Solves the Cocktail Party Problem

The cocktail party effect is the ability to focus on a specific human voice while filtering out other voices or background noise.

particularly challenging cocktail party problem is in the field of music, where humans can easily concentrate on a singing voice superimposed on a musical background that includes a wide range of instruments.

These guys have used some of the most recent advances associated with deep neural networks to separate human voices from the background in a wide range of songs.

And it paves the way for a more general solution to the famous cocktail party problem which should allow, among other things, the vocals to be easily separated from the music they accompany.

They start with a database of 63 songs that are available as a set of individual tracks that each contain a different instrument or voice, as well as the fully mixed version of the song.

So the network begins with these parameters set randomly and then gradually improves the settings each time it scans through the database, which it did over a hundred iterations.

“These results demonstrate that a convolutional deep neural network approach is capable of generalizing voice separation, learned in a musical context, to new musical contexts,” say the team.

Simpson and co of even compared their results to those from a conventional cocktail party algorithm applied to the same data. “The main advantage of the deep neural network appears to be in its general learning of what ‘vocal’ sounds are,” they say.

Computer tries to replicate my voice!

Skip to 9:27 if you want to hear the computer speaking (and not the process by which I made it happen). The comment was originally by ContactingTheDead, ...

MIT 6.S094: Recurrent Neural Networks for Steering Through Time

This is lecture 4 of course 6.S094: Deep Learning for Self-Driving Cars taught in Winter 2017. Course website: Lecture 4 slides: ..

Librosa Audio and Music Signal Analysis in Python | SciPy 2015 | Brian McFee

Lecture 10.2 Source Signal Feature Extraction

Introduction to Modern Brain-Computer Interface Design - Christian A. Kothe Swartz Center for Computational Neuroscience, University of California San Diego.

ISSE: An Interactive Source Separation Editor

Full Title: ISSE: An Interactive Source Separation Editor Authors: Nicholas J Bryan, Gautham J Mysore, Ge Wang Abstract: Traditional audio editing tools do not ...

Dean Buonomano: "Your Brain is a Time Machine" | Talks at Google

In YOUR BRAIN IS A TIME MACHINE, UCLA neuroscientist Dean Buonomano investigates the relationship between the brain and time: What is time? Why does ...

NIPS 2011 Music and Machine Learning Workshop: Multi-Timescale Principal Mel Spectral Components..

International Music and Machine Learning Workshop: Learning from Musical Structure at NIPS 2011 Invited Talk: Multi-Timescale Principal Mel Spectral ...

2011 Frontiers of Engineering: Ultra Low Power Biomedical and Bio-inspired Systems

National Academy of Engineering 2011 U.S. Frontiers of Engineering Symposium September 19-21, 2011 Google, Inc. Mountain View, California Ultra Low ...


Humanities Innovators in a Tech World | Thursday May 17th

Sponsored by the Dorrance Scholarship Programs, the College of Humanities presents "Humanities Innovators in a Tech World," the first symposium in the ...