Transcription and Recognition of Syllable based Percussion Patterns: The Case of Beijing Opera

In many cultures of the world, traditional percussion music uses mnemonic syllables that are representative of the timbres of instruments. These syllables are orally transmitted and often provide a language for percussion in those music cultures. Percussion patterns in these cultures thus have a well defined representation in the form of these syllables, which can be utilized in several computational percussion pattern analysis tasks. We explore a connected word speech recognition based framework that can effectively utilize the syllabic representation for automatic transcription and recognition of audio percussion patterns. In particular, we consider the case of Beijing opera and present a syllable level hidden markov model (HMM) based system for transcription and classification of percussion patterns. The encouraging classification results on a representative dataset of Beijing opera percussion patterns supports our approach and provides further insights on the utility of these syllables for computational description of percussion patterns.