Speech Prosody 2010
Chicago, IL, USA
An analysis is presented on the rate of inter-speaker consistency in the way multiple speakers realize prosodic events when they read the same scripts. The analysis is made on the Boston University Radio Speech Corpus (BURSC). The BURSC consists of data from five speakers (3 female and 2 male), each reading the same scripts that comprise more than 110 different sentences. The design of the corpus, thus, proves to be a useful basis on which we can measure the degree of speaker variation or speaker consistency in prosodic realization. A pair-wise comparison of inter-speaker consistency is made regarding the rendition of prosodic prominence. The results indicate that the average rate of consistency on the presence or absence of pitch accent is 89.81%. An average consistency of 72.17% is achieved for the rate of consistency for the types of the pitch accent. The finding implies that there is a constraint that is imposed on an utterance by speakers regarding prosodic prominence placement, as well as certain degree of variation between speakers in rendering prosodic prominence.
Bibliographic reference. Yoon, Tae-Jin (2010): "Speaker consistency in the realization of prosodic prominence in the Boston University Radio Speech Corpus", In SP-2010, paper 2012.