2026-04-12T11:51:00Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00176408 2025-01-20T05:53:06Z 1164:5159:8497:9012

A comparative study on modeling and controlling emotional acoustic parameters in neural networks based Japanese and Spanish speech synthesis A comparative study on modeling and controlling emotional acoustic parameters in neural networks based Japanese and Spanish speech synthesis Jaime, Lorenzo-Trueba Shinji, Takaki Junichi, Yamagishi Jaime, Lorenzo-Trueba Shinji, Takaki Junichi, Yamagishi 音声合成 In neural network based speech synthesis, adding a one-hot vector to the input is an easy, intuitive but useful way to model multiple speakers or multiple language. In this paper, we use the one-hot vector for modeling and controlling emotional acoustic parameters. We have used Spanish and Japanese databases having the multiple acted emotional speech uttered by professional speakers in our experiment and will show the performance of the one-hot vector approach. In neural network based speech synthesis, adding a one-hot vector to the input is an easy, intuitive but useful way to model multiple speakers or multiple language. In this paper, we use the one-hot vector for modeling and controlling emotional acoustic parameters. We have used Spanish and Japanese databases having the multiple acted emotional speech uttered by professional speakers in our experiment and will show the performance of the one-hot vector approach. technical report 情報処理学会 2016-12-13 application/pdf 研究報告音声言語情報処理（SLP） 22 2016-SLP-114 1 6 2188-8663 AN10442647 https://ipsj.ixsq.nii.ac.jp/record/176408/files/IPSJ-SLP16114022.pdf eng