05-02-2021: ADASP has 4 papers accepted at ICASSP 2021
Here are the four ADASP papers that will be presented at ICASSP 2021: ≥≥
The ADASP group (Audio Data Analysis and Signal Processing, formerly known as the AAO group) is a research subgroup of the S²A team, affiliated with Telecom Paris’ in-house research laboratory: the LTCI.
A significant fraction of our research is performed within national and international collaborative projects, with numerous academic and industrial partners.
Here are the four ADASP papers that will be presented at ICASSP 2021: ≥≥
ADASP is proud of its member and former coordinator Gaël Richard being laureate of 2020 IMT-Academie des Sciences Grand Prix. ≥≥
F. Foscarin presents his work on pitch spelling and key signature estimation ≥≥
A. Lerch talks to ADASP about his work on unsupervised and semi-supervised approaches for addressing the data challenge in music analysis ≥≥
J. Pauwels talks to ADASP about evaluation without ground-truth in the data-driven age. ≥≥
M. Fontaine talks to ADASP about Gaussian scale mixture representation for blind source separation ≥≥
Thomas Arvanitidis talks to ADASP about MUSIC Tribe’s perspectives and challenges arisen from deploying ML-driven audio applications on edge. ≥≥
Furkan Yesiler explains to ADASP his work on deep learning-based musical version identification. ≥≥
Our group is hiring an intern in machine learning for audio signal processing. ≥≥
In our paper (Cífka et al., 2021), we present a novel method for one-shot timbre style transfer, based on the vector-quantized variational autoencoder (VQ-VA... ≥≥
Sixin Zhang tells ADASP how to characterize learnable structures from high-dimensional data. ≥≥
The html-midi-player package provides the <midi-player> and <midi-visualizer> HTML elements, which make it easy to play and display MIDI files on... ≥≥
Our group is hiring an associate professor in machine learning for distributed/multi-view machine listening and audio content analysis. ≥≥
This library provides tools for working with common MIR datasets, including tools for: ≥≥
The Groove2Groove MIDI Dataset is a parallel corpus of synthetic MIDI accompaniments in almost 3000 different styles. The accompaniments were created from ch... ≥≥
Groove2Groove (Grv2Grv) is an AI system for music accompaniment style transfer. Given two MIDI files – a content input and a style input – it generates a new... ≥≥
Stefan Lattner explains to ADASP the mechanisms of transformation and invariance learning for symbolic music and audio. ≥≥