Generating Segment Durations in a Text-To-Speech System: A Hybrid Rule-Based/Neural Network Approach

Details Generating Segment Durations in a Text-To-Speech System: A Hybrid Rule-Based/Neural Network Approach Generating Segment Durations in a Text-To-Speech System: A Hybrid Rule-Based/Neural Network Approach

1998-11-24

arxiv.org/abs/cs/9811030v1

Proceedings of Eurospeech (1997) 2675-2678. Rhodes, Greece

Computer Science

Neural and Evolutionary Computing

4 pages, PostScript

Scientific paper

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 the same quality as speech generated using segment durations extracted from natural speech.

Affiliated with

Also associated with

No associations

Rating

Generating Segment Durations in a Text-To-Speech System: A Hybrid Rule-Based/Neural Network Approach does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Generating Segment Durations in a Text-To-Speech System: A Hybrid Rule-Based/Neural Network Approach, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Generating Segment Durations in a Text-To-Speech System: A Hybrid Rule-Based/Neural Network Approach will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-458940