Explicit Transition Modelling for Automatic Singing Transcription
Willie Krige, Theo Herbst, Thomas Niesler · Journal of New Music Research · 2008
We present a system for the automatic transcription of solo human singing into note sequences. Particular attention is devoted to the modelling of the transitions between consecutive notes of the sung passage. Hidden Markov models (HMMs) are used to represent both individual notes and the transitions between them, in order to capture the variability of the estimated pitch within a statistical framework. A database consisting of annotated passages sung by 26 soprano subjects is compiled and used for the development of the system. Explicit transition models are introduced in order to better identify note boundaries that are otherwise poorly modelled. Context-independent transition models are evaluated first, followed by context-dependent transition models which are shown to improve both the note recognition accuracy and the transition region time-alignment. The final system is found to be able to transcribe sung passages with an overall accuracy of 86.7%.