Paper: Unsupervised And Semi-Supervised Learning Of Tone And Pitch Accent

ACL ID N06-1029
Title Unsupervised And Semi-Supervised Learning Of Tone And Pitch Accent
Venue Human Language Technologies
Session Main Conference
Year 2006
Authors

Recognition of tone and intonation is es- sential for speech recognition and lan- guage understanding. However, most ap- proaches to this recognition task have re- lied upon extensive collections of man- ually tagged data obtained at substantial time and financial cost. In this paper, we explore two approaches to tone learn- ing with substantially reductions in train- ing data. We employ both unsupervised clustering and semi-supervised learning to recognize pitch accent in English and tones in Mandarin Chinese. In unsu- pervised Mandarin tone clustering exper- iments, we achieve 57-87% accuracy on materials ranging from broadcast news to clean lab speech. For English pitch accent in broadcast news materials, results reach 78%. In the semi-supervised framework, we achieve Mandarin tone reco...