Title :
A statistical text-to-phone function using ngrams and rules
Author :
Fisher, William M.
Author_Institution :
Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
Abstract :
Adopting concepts from statistical language modeling and rule-based transformations can lead to effective and efficient text-to-phone (TTP) functions. We present here the methods and results of one such effort, resulting in a relatively compact and fast set of TTP rules that achieves 94.5% segmental phonemic accuracy
Keywords :
knowledge based systems; speech synthesis; statistical analysis; TTP rules; effective efficient text-to-phone; ngrams; rule-based transformations; segmental phonemic accuracy; statistical language modeling; statistical text-to-phone function; Automatic speech recognition; Data structures; Dictionaries; NIST; Natural languages; Predictive models; Probability distribution; Speech processing; Speech synthesis; Text recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on
Conference_Location :
Phoenix, AZ
Print_ISBN :
0-7803-5041-3
DOI :
10.1109/ICASSP.1999.759750
