The music language model performs voice separation and assignment using hidden Markov models that apply musicological assumptions. The acoustic model performs spectrogram decomposition, extending probabilistic latent component analysis (PLCA) using a six-dimensional dictionary with pre-extracted log-spectral templates. We propose a system for multi-pitch detection and voice assignment that integrates an acoustic and a music language model. N2 - This paper presents a method for automatic music transcription applied to audio recordings of a cappella performances with multiple singers. T1 - Automatic Transcription of Polyphonic Vocal Music We also present an additional evaluation of our system using varied pitch tolerance levels to investigate its performance at 20-cent pitch resolution.", We compare our system against multiple baselines, achieving state-of-the-art results for both multi-pitch detection and voice assignment on a dataset of Bach chorales and another of barbershop quartets. By integrating the two models, the system is able to detect multiple concurrent pitches in polyphonic vocal music and assign each detected pitch to a specific voice type such as soprano, alto, tenor or bass (SATB).
We also present an additional evaluation of our system using varied pitch tolerance levels to investigate its performance at 20-cent pitch resolution.Ībstract = "This paper presents a method for automatic music transcription applied to audio recordings of a cappella performances with multiple singers.
This paper presents a method for automatic music transcription applied to audio recordings of a cappella performances with multiple singers.