Dependency Analysis of Read Japanese Sentences using Pause and F0 Information: A Speaker Independent Case

摘要

This paper deals with the problem of exploiting prosodic information in syntactic analysis of sentences. Duration of pauses at phrase boundaries and relative F_0 contour features have been found to be effective for parsing in speaker-dependent case. In this paper, effectiveness of pause and F_0 information was examined in a speaker-independent manner by using prosodic features extracted from the spoken version of sentences of 44 speakers. By simplifying the estimation of both pause and F_0 contour models, better performance was obtained. Linear combination of pause and F_0 information gave significant improvements in parsing accuracy. It was also shown that the effectiveness of pause information was larger when pause models were estimated separately for zero-duration and non-zero-duration pauses.