EXPLICIT DURATION HIDDEN MARKOV MODELS FOR MULTIPLE-INSTRUMENT POLYPHONIC MUSIC TRANSCRIPTION

In this paper, a method for multiple-instrument automatic music transcription is proposed that models the temporal evolution and duration of tones. The proposed model sup-ports the use of spectral templates per pitch and instrument which correspond to sound states such as attack, sustain, and decay. Pitch-wise explicit duration hidden Markov models (EDHMMs) are integrated into a convolutive prob-abilistic framework for modelling the temporal evolution and duration of the sound states. A two-stage transcrip-tion procedure integrating note tracking information is per-formed in order to provide more robust pitch estimates. The proposed system is evaluated on multi-pitch detection and instrument assignment using various publicly available datasets. Results show that the proposed system outper-forms a hidden Markov model-based transcription system using the same framework, as well as several state-of-the-art automatic music transcription systems. 1