ARX音声生成モデルに基づいた音声分析・合成・編集システム

概要

論文の詳細を見る
We present a new formant-type speech analysis-synthesis-editing system based on the ARX(Auto-Regressive with Exogenous Input) speech production model. One of the key features of the proposed system is implementation of the algorithm that automatically estimates voicing and unvoiced source parameters as well as formant-antiformant parameters of the synthesizer directly from a speech utterance. After automatically estimating the parameters from the utterance, one can manipulate the estimates using a flexible editing tool that has been developed as a part of the system. Using the parameter values so modified, one can synthesize speech with various voice qualities. Since the system has been developed on the MS-Windows platform, it is expected to be a useful tool in various areas of speech research.
社団法人日本音響学会の論文
1998-03-00