Abstract
To compensate for the variability in native English intonation and the unpredictability of normative speech, we propose a new method of assessing normative intonation without any prior knowledge of the target text or phonetics. After recognition of tone events with HMMs and a bigram model of intonation, we define an utterance's automatic intonation score as the mean of the posterior probabilities for all recognized tone segments. On the ISLE corpus of learners' English, we find intonation scores generated by this technique have a 0.331 correlation with general pronunciation scores determined by native listeners. In comparison, the SRI Eduspeak system's proposal for pronunciation scoring based on suprasegmental features derived from prior knowledge of the target text yields a 0.247 correlation with listener scores on a similar corpus. Because it is text-free, our approach could be used to assess intonation outside of a strictly educational application.