Speech synthesis system

专利名称：Speech synthesis system发明人：Richard Anthony Sharman申请号：US08/391731申请日：19950221公开号：US05682501A公开日：19971028

摘要：A speech synthesis unit comprises a text processor which breaks down text intophonemes, a prosodic processor which assigns properties such as length and pitch to thephonemes based on context, and a synthesis unit which outputs an audio signalrepresenting the sequence of phonemes according to the specified properties. Theprosodic processor includes a Hidden Markov Model (HMM) to predict the durations ofthe phonemes. Each state of the HMM represents a duration, and the outputs arephonemes. The HMM is trained on a set of data consisting of phonemes of knownidentity and duration, to allow the state transition and output distributions to becalculated. The HMM can then be used for any given input sequence of phonemes topredict a most likely sequence of corresponding durations.

申请人：INTERNATIONAL BUSINESS MACHINES CORPORATION

代理机构：Whitham, Curtis, Whitham & McGinn

代理人：Robert P. Tassinari, Jr.

更多信息请下载全文后查看