/ismir2022-datasets

list of MIR dataset papers presented at ISMIR 2022

ismir2022-datasets

A list of (27) papers introducing MIR datasets presented at ISMIR 2022.

Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model

Scaling Polyphonic Transcription with Mixtures of Monophonic Transcriptions

YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotations

AccoMontage2: A Complete Harmonization and Accompaniment Arrangement System

Playing Technique Detection by Fusing Note Onset Information in Guzheng Performance

KDC: an open corpus for computational research of dastgāhi music

Automatic Chinese National Pentatonic Modes Recognition Using Convolutional Neural Network

Teach Yourself Georgian Folk Songs Dataset: A Annotated Corpus Of Traditional Vocal Polyphony

A Dataset for Greek Traditional and Folk Music: Lyra

Analysis and detection of singing techniques in repertoires of J-POP solo singers

ATEPP: A Dataset of Automatically Transcribed Expressive Piano Performance

Parameter Sensitivity of Deep-Feature based Evaluation Metrics for Audio Textures

Multi-pitch Estimation meets Microphone Mismatch: Applicability of Domain Adaptation

Melody transcription via generative pre-training

A Dataset of Symbolic Texture Annotations in Mozart Piano Sonatas

Violin Etudes: A Comprehensive Dataset for f0 Estimation and Performance Analysis

Symphony Generation with Permutation Invariant Language Model

Towards robust music source separation on loud commercial music

Towards Quantifying the Strength of Music Scenes Using Live Event Data

Improving Choral Music Separation through Expressive Synthesized Data from Sampled Instruments

Emotion-driven Harmonisation And Tempo Arrangement of Melodies Using Transfer Learning

EnsembleSet: a new high quality synthesised dataset for chamber ensemble separation

MusAV: A dataset of relative arousal-valence annotations for validation of audio models

Robust Melody Track Identification in Symbolic Music

Tracking the Evolution of a Band's Live Performances over Decades

A Novel Dataset and Deep Learning Benchmark for Classical Music Form Recognition and Analysis

BAF: An audio fingerprinting dataset for broadcast monitoring