Gerald Corrigan

Learn More
A combination of a neural network with rule firing information from a rule-based system is used to generate segment durations for a text-to-speech system. The system shows a slight improvement in performance over a neural network system without the rule firing information. Synthesized speech using segment durations was accepted by listeners as having about(More)
This paper describes the design of a neural network that performs the phonetic-to-acoustic mapping in a speech synthesis system. The use of a time-domain neural network architecture limits discontinuities that occur at phone boundaries. Recurrent data input also helps smooth the output parameter tracks. Independent testing has demonstrated that the voice(More)
I am pleased to appear before you to discuss the role of central banks and the financial system in the specific context of the recent efforts on the part of a number of Eastern European countries and the Soviet Union to shift their economies toward more market-oriented and competitive systems. I am especially pleased to have the opportunity to discuss these(More)
While neural networks have been employed to handle several different text-to-speech tasks, ours is the first system to use neural networks throughout, for both linguistic and acoustic processing. We divide the text-to-speech task into three subtasks, a linguistic module mapping from text to a linguistic representation, an acoustic module mapping from the(More)
JAMES McCARTIN: Well, I would say there are certain things that haven't changed in the post-conciliar Church by the behavior of this audience. You were very compliant, for which I am very grateful. [Laughter] Thanks for being so cooperative yesterday and throughout today. First of all, I want to just say a quick word about how impressed I have been with the(More)
A combination of a neural network with rule firing information from a rule-based system is used to generate segment durations for a text-to-speech system. The system shows a slight improvement in performance over a neural network system without the rule firing information. Synthesized speech using segment durations was accepted by listeners as having about(More)
  • 1