Search Results 1-8 of 8

  • Joint Adversarial Training of Speech Recognition and Synthesis Models for Many-to-One Voice Conversion Using Phonetic Posteriorgrams

    SAITO Yuki , AKUZAWA Kei , TACHIBANA Kentaro

    … <p>This paper presents a method for many-to-one voice conversion using phonetic posteriorgrams (PPGs) based on an adversarial training of deep neural networks (DNNs). … A conventional method for many-to-one VC can learn a mapping function from input acoustic features to target acoustic features through separately trained DNN-based speech recognition and synthesis models. …

    IEICE Transactions on Information and Systems E103.D(9), 1978-1987, 2020

    J-STAGE 

  • DNN-based Voice Conversion with Auxiliary Phonemic Information to Improve Intelligibility of Glossectomy Patients' Speech

    Murakami Hiroki

    … Our previous studies showed that voice conversion algorithm improves the quality of glossectomy patients' speech. … To combine both acoustic features and PLA, we employed a DNN-based algorithm. …

    Proceedings of APSIPA Annual Summit and Conference (2019), 138-142, 2019-11

    IR 

  • DNN Based Voice Conversion Method Considering Outputs of Multiple Networks  [in Japanese]

    藤岡 拓也 , 孫 慶華

    聴覚研究会資料 = Proceedings of the auditory research meeting 48(1), 11-15, 2018-01-20

  • DNN Based Voice Conversion Method Considering Outputs of Multiple Networks  [in Japanese]

    藤岡 拓也 , 孫 慶華

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 117(393), 11-15, 2018-01-20

  • Evaluation of DNN-Based Voice Conversion Deceiving Anti-spoofing Verification  [in Japanese]

    齋藤 佑樹 , 高道 慎之介 , 猿渡 洋

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 116(414), 29-34, 2017-01-21

  • Voice Conversion Using Input-to-Output Highway Networks

    SAITO Yuki , TAKAMICHI Shinnosuke , SARUWATARI Hiroshi

    … <p>This paper proposes Deep Neural Network (DNN)-based Voice Conversion (VC) using input-to-output highway networks. … VC is a speech synthesis technique that converts input features into output speech parameters, and DNN-based acoustic models for VC are used to estimate the output speech parameters from the input speech parameters. …

    IEICE Transactions on Information and Systems E100.D(8), 1925-1928, 2017

    J-STAGE 

  • Voice conversion based on deep neural network with multiple output sub-networks  [in Japanese]

    HASHIMOTO Tetsuya , KASHIWAGI Yousuke , SAITO Daisuke , HIROSE Keikichi , MINEMATSU Nobuaki

    … 本研究では,話者性の柔軟な制御に向けてのDeep Neural Network(DNN)による声質変換手法を提案する.DNNでは,既存手法であるGaussian Mixture Models(GMM)よりも高精度の変換が可能であるという報告もされているが,DNNは各ノード・各レイヤーがどういった情報を扱い,どのような変換を行っているかが不明瞭であるため,GMMのようなパラメータ適応が難しく,柔軟な変換を実現することが難しいとい …

    IEICE technical report. Speech 114(365), 99-104, 2014-12-15

  • Voice conversion based on deep neural network with multiple output sub-networks  [in Japanese]

    Tetsuya Hashimoto , Yousuke Kashiwagi , Daisuke Saito , Keikichi Hirose , Nobuaki Minematsu

    … 本研究では,話者性の柔軟な制御に向けてのDeep Neural Network(DNN) による声質変換手法を提案する.DNN では,既存手法である Gaussian Mixture Models(GMM) よりも高精度の変換が可能であるという報告もされているが,DNN は各ノード・各レイヤーがどういった情報を扱い,どのような変換を行っているかが不明瞭であるため,GMM のようなパラメータ適応が難しく,柔軟な変換を実現することが難しい …

    IPSJ SIG Notes 2014-SLP-104(19), 1-6, 2014-12-08

Page Top