Addressing the Recitative Problem in Real-time Opera Tracking

TL;DR

This paper improves real-time opera tracking by using dual trackers focused on music and speech features, addressing challenges during recitative passages for more accurate alignment in live settings.

Contribution

It introduces a novel dual-tracker approach combining music and speech classifiers to enhance score following accuracy during recitative sections.

Findings

Dual trackers improve alignment accuracy during recitatives.

Speech features help distinguish recitative passages from music.

Combining classifiers yields more robust real-time opera tracking.

Abstract

Robust real-time opera tracking (score following) would be extremely useful for many processes surrounding live opera staging and streaming, including automatic lyrics displays, camera control, or live video cutting. Recent work has shown that, with some appropriate measures to account for common problems such as breaks and interruptions, spontaneous applause, various noises and interludes, current audio-to-audio alignment algorithms can be made to follow an entire opera from beginning to end, in a relatively robust way. However, they remain inaccurate when the textual content becomes prominent against the melody or music -- notably, during recitativo passages. In this paper, we address this specific problem by proposing to use two specialized trackers in parallel, one focusing on music-, the other on speech-sensitive features. We first carry out a systematic study on speech-related features, targeting the precise alignment of corresponding recitatives from different performances of the same opera. Then we propose different solutions, based on pre-trained music and speech classifiers, to combine the two trackers in order to improve the global accuracy over the course of the entire opera.