Determining pitch accents in a sentence is a key task for a text-to-speech (TTS) system. We describe some methods for pitch accent assignment which make use of features that contain information about a complete phrase or sentence, in contrast to most previous work which has focused on using features local to a syllable or word. Pitch accent prediction is performed using three different techniques: N-gram models of syllable sequences, dynamic programming to match sequences of features, and decision trees. Using a C4.5 decision tree trained on a wide range of features, most notably each word's orthographic form and information extracted from the syntactic parse of the sentence, our feature set achieved a balanced error rate of 46.6%. This compares with the feature set used in  which had a balanced error rate of 55.55%.
|Number of pages||4|
|Publication status||Published - 2007|
|Event||8th Annual Conference of the International Speech Communication Association (INTERSPEECH-2007) - Antwerp, Belgium|
Duration: 27 Aug 2007 → 31 Aug 2007
|Conference||8th Annual Conference of the International Speech Communication Association (INTERSPEECH-2007)|
|Period||27/08/07 → 31/08/07|