Automatic Assessment of Singing Voice Pronunciation: A Case Study with Jingju Music

TitleAutomatic Assessment of Singing Voice Pronunciation: A Case Study with Jingju Music
Publication TypePhD Thesis
Year of Publication2018
UniversityUniversitat Pompeu Fabra
AuthorsGong, R.
AdvisorSerra, X.
Academic DepartmentDepartment of Information and Communications Technologies
Number of Pagesxxxii + 235
Date Published11/2018
CityBarcelona
Keywordsacoustic embedding, automatic assessment, Beijing opera, hmm, jingju, neural networks, pronunciation, similarity, singing voice
Final publicationhttps://doi.org/10.5281/zenodo.1490343
Full TextThis dissertation aims to develop data-driven audio signal processing and machine learning (deep learning) models for automatic singing voice assessment in audio collections of jingju music. We identify challenges and opportunities, and present several research tasks relevant to automatic singing voice assessment of jingju music. Data-driven computational approaches require well-organized data for model training and testing, and we report the process of curating the data collections (audio and editorial metadata) in detail. We then focus on the research topics of automatic syllable and phoneme segmentation, automatic mispronunciation detection and automatic pronunciation similarity measurement in jingju music.
Additional material: 
intranet