Three talks on Deep-learning for music processing

Three talks on Deep-learning for music processing

Friday November 15 at 15:30 in room 55.309 (Universitat Pompeu Fabra, Poblenou campus)


Imatge inicial

15:30 - Geoffroy Peeters (Télécom Paris): Depth, triplet and conditioning for deep-MIR

Bio: Geoffroy Peeters received his PHD on signal processing for speech processing in 2001 and his Habilitation (HDR) on Music Information Retrieval in 2013 from University Paris VI. From 2001 to 2018, he led research related to MIR at IRCAM. His research topics concern signal processing and machine learning (including deep learning) for the automatic analysis of music (timbre description, audio features, singing voice, source separation, beat/downbeat/rhythm estimation, chord/key/multi-pitch estimation, music structure/summary, audio-identification, cover-version, auto-tagging), evaluation methodologies and corpus creation. Since 2018, he his full professor in the Image-Data-Signal department of Télécom Paris, Institut Polytechnique de Paris where he teaches those topics. He is the author of numerous articles and several patents in these areas and co-author of the ISO MPEG-7 audio standard. He has been co-general chair of the DAFx-2011 and ISMIR-2018 conferences and is member of the DAFx board, IEEE Task Force on Computational Audio Processing and has been elected in the ISMIR board in 2016.

16:30 - Juhan Nam (KAIST):  Deep Metric Learning for Music: Beyond the Conventional Classification Framework

Bio: Juhan Nam is an associate professor at Korea Advanced Institute of Science and Technology (KAIST), South Korea. He received his Ph.D. degree in Music from Stanford University in 2013, studying at the Center for Computer Research in Music and Acoustics (CCRMA). Before joining KAIST, he was a staff research engineer at Qualcomm from 2012 to 2014. He was also a software/digital signal processing engineer at Young Chang (Kurzweil) from 2001 to 2006.

17:00 - Fabian-Robert Stöter (Inria): Open-Unmix: tools for reproducible music separation research

Bio: Fabian-Robert Stöter received the diploma degree in electrical engineering in 2012 from the Leibniz Universität Hannover and worked towards his Ph.D. degree in audio signal processing in the research group of Bernd Edler at the International Audio Laboratories Erlangen, Germany. He is currently researcher at Inria, France. His research interests include supervised and unsupervised methods for audio source separation and signal analysis of highly overlapped sources.