Language identification for singing

In spoken language processing, considerable research has been accomplished on language identi cation. Singing language identi cation is an important yet challenging area that has attracted only a few researchers in music processing. As one information source that can be extracted from music, the language of vocal music is useful for song classi cation, recognition, and retrieval based on the singing language, specially in unlabeled or mislabeled music collections. In addition, consideration of singing as a speaking style introduces new challenges to existing language identi cation systems. Our objective in this paper, as one of the rst attempts for singing language identi cation, is to evaluate successful LID systems, speci cally PPRLM with singing speech. Furthermore, we propose a prosodic approach based on pitch contour approximation and compare the results to PPRLM system. Language identi cation performance for singing and read speech are compared in both systems. Finally, we combi...

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Mahnoosh Mehrabani, John H. L. Hansen
• Keywords: ICASSP 2011, Identi Cation Systems, Language Identi Cation, Signal Processing, Song Classi Cation