arXivDaily arXiv每日学术速递 周一至周五更新
arXiv cs/9811030cs.NEcs.HC
收藏

一种基于规则/神经网络的文语转换系统中的段时长生成方法

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

Gerald Corrigan, Noel Massey, Orhan Karaali

摘要:

使用神经网络与来自基于规则的系统的规则激发信息的组合来生成文本到语音系统的段持续时间。该系统在性能上比没有规则激发信息的神经网络系统略有提高。使用段持续时间的合成语音被听众接受为具有与使用从自然语音提取的段持续时间生成的语音大约相同的质量。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑