Refining phoneme segmentations using speaker-adaptive context dependent boundary models

Consistent phoneme segmentation is essential in building high quality Text-to-Speech (TTS) voice fonts. In this paper we propose to adapt an existing well-trained Context Dependent Boundary Model (CDBM) for refining segment boundaries to a new speaker with limited, manually segmented data. Three adaptation approaches: MLLR, MAP, and a combination of the two, are studied. The combined one, MLLR+MAP, delivers the best boundary refinement performance. In comparison with other boundary segmentation methods, the adapted CDBM yields better results, especially with a limited amount of adaptation data. Given 400 manually segmented boundary tokens in about 20 sentences as a development set, the segmentation precision can reach 90% of human labeled boundaries within a tolerance of 20 ms.