Automatic music transcription: challenges and future directions

328 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Onsets and Frames: Dual-Objective Piano Transcription (2017, background): “[3] noted in their review paper in 2013, “evaluating the performance of current [automatic music transcription] systems for the estimation of note dynamics has not yet been addressed.”
Automatic Music Transcription: An Overview (2019, background): “, notes and percussive sounds) that are meant to be highly correlated over both time and frequency, AMT is still considered a challenging and open problem in the literature, particularly for music containing multiple instruments and many simultaneous notes (called polyphonic music in the music signa”
M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus (2022, background): “Note-level automatic music transcription (AMT) refers to converting a recorded music piece into its symbolic form containing the onset, offset, and pitch of every note [3; 32].”
Multi-resolution linear prediction based features for audio onset detection with bidirectional LSTM neural networks (2014, unknown): “Automatic detection of events in audio signals is exploited in many audio applications including content delivery, compression, indexing, retrieval [1], automatic music transcription [2, 3, 4, 5, 6], and beat detection [7].”