This paper presents and evaluates a phonological phrase parser for a Spanish text-to-speech system. The parser consists of three stages: 1) lexical lookup, using a small dictionary (428 words); 2) preliminary phrase boundary placement, using a modification of Liberman and Church's (1992) function group parser; and 3) readjustment of phrase boundaries, using syllable count and punctuation. A corpus of 382 hand-parsed sentences (1,691 phrases) was used to evaluate the parser. The parser generated almost the same number of phrases (1,692) as the hand-parsed sentences with 70% (1,186) agreement. Suggestions for improving the parser's performance include the expansion of the verb lexicon, performing simple morphological analysis for verbs, and relaxing the syllable count in phrases before verb forms.

Abstract not found

We propose a dialog act classification based on the prosody of the audio signal in combination with the course of the dialog. The work is applied to the Spanish corpus DIHANA. As far as we know, it is the first experiment made with prosody in this corpus. To do the labeling, we used two features that had been extracted from the user speech (pitch and energy) in a HMM classifier combined with an n-gram of dialog acts. The results shows a sightly improvement in the tagging when prosody is included in the classification. 1.