[AUDITORY] CFP: ML4Audio @xxxxxxxx NIPS2017 (Hendrik Purwins )


Subject: [AUDITORY] CFP: ML4Audio @xxxxxxxx NIPS2017
From:    Hendrik Purwins  <hpurwins@xxxxxxxx>
Date:    Fri, 22 Sep 2017 16:30:20 +0200
List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>

Apologies for cross-posting: Audio signal processing is currently undergoing a paradigm change, where=20 data-driven machine learning is replacing hand-crafted feature design.=20 This has led some to ask whether audio signal processing is still useful=20 in the "era of machine learning." There are many challenges, new and=20 old, including the interpretation of learned models in high dimensional=20 spaces, problems associated with data-poor domains, adversarial=20 examples, high computational requirements, and research driven by=20 companies using large in-house datasets that is ultimately not reproducib= le. ML4Audio (https://nips.cc/Conferences/2017/Schedule?showEvent=3D8790) aim= s=20 to promote progress, systematization, understanding, and convergence of=20 applying machine learning in the area of audio signal processing.=20 Specifically, we are interested in work that demonstrates novel=20 applications of machine learning techniques to audio data, as well as=20 methodological considerations of merging machine learning with audio=20 signal processing. We seek contributions in, but not limited to, the=20 following topics: - audio information retrieval using machine learning; - audio synthesis with given contextual or musical constraints using=20 machine learning; - audio source separation using machine learning; - audio transformations (e.g., sound morphing, style transfer) using=20 machine learning; - unsupervised learning, online learning, one-shot learning,=20 reinforcement learning, and incremental learning for audio; - applications/optimization of generative adversarial networks for audio; - cognitively inspired machine learning models of sound cognition; - mathematical foundations of machine learning for audio signal processin= g. ML4Audio will accept five kinds of submissions: 1. novel unpublished work, including work-in-progress; 2. recent work that has been already published or is in review (please=20 clearly refer to the primary publication); 3. review-style papers; 4. position papers; 5. system demonstrations. Submission format: Extended abstracts as pdf in NIPS paper format, 2-4=20 pages, excluding references. Submissions do not need to be anonymised.=20 Submissions might be either accepted as talks or as posters. If=20 accepted, final papers must be uploaded on arxiv.org. Submission link: https://easychair.org/conferences/?conf=3Dml4audio Important Dates: Submission Deadline: October 20, 2017 Acceptance Notification: October 31, 2017 Camera Ready Submissions: November 30, 2017 Workshop: Dec 8, 2017 (Note that the main conference is sold out already. Presenters of=20 accepted workshop papers will still be able to register for the workshops= .) This workshop especially targets researchers, developers and musicians=20 in academia and industry in the area of MIR, audio processing, speech=20 processing, musical HCI, musicology, music technology, music=20 entertainment, and composition. Invited Speakers: Sander Dieleman (Google DeepMind) Douglas Eck (Google Magenta) Marco Marchini (Spotify) Others to be decided Panel Discussion: Sepp Hochreiter (Johannes Kepler University Linz), Invited speakers Others to be decided ML4Audio Organisation Committee: - Hendrik Purwins, Aalborg University Copenhagen, Denmark=20 (hpu@xxxxxxxx) - Bob L. Sturm, Queen Mary University of London, UK (b.sturm@xxxxxxxx) - Mark Plumbley, University of Surrey, UK (m.plumbley@xxxxxxxx) PROGRAM COMMITTEE: Sebastian B=C3=B6ck (Johannes Kepler University Linz) Matthias Dorfer (Johannes Kepler University Linz) Monika D=C3=B6rfler (University of Vienna) Shlomo Dubnov (UC San Diego) Philippe Esling (IRCAM) C=C3=A9dric F=C3=A9votte (IRIT) Mads Gr=C3=A6sb=C3=B8ll (Aalborg University) Emilia G=C3=B3mez (Universitat Pompeu Fabra) Jan Larsen (Danish Technical University) Marco Marchini (Spotify) Rafael Ramirez (Universitat Pompeu Fabra) Ga=C3=ABl Richard (TELECOM ParisTech) Jan Schl=C3=BCter (Austrian Research Institute for Artificial Intelligenc= e) Joan Serr=C3=A0 (Telefonica) Malcolm Slaney (Google) Gerhard Widmer (Austrian Research Institute for Artificial Intelligence) Others to be decided


This message came from the mail archive
../postings/2017/
maintained by:
DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University