Unsupervised Learning of Tone and Pitch Accent

Recognition of tone and intonation is essential for speech recog-nition and language understanding. However, most approaches to this recognition task have relied upon extensive collections of manually tagged data obtained at substantial time and finan-cial cost. In this paper, we explore unsupervised clustering ap-proaches to recognize pitch accent in English and tones in Man-darin Chinese. In unsupervised 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%. These results indi-cate that the intrinsic structure of tone and pitch accent acoustics can be exploited to reduce the need for costly labeled training data for tone learning and recognition. 1