PRISM: Speech privacy preservation based on selecting masking

• Project/Area Number: 18H04112
• Research Category: Grant-in-Aid for Scientific Research (A)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Medium-sized Section 61:Human informatics and related fields
• Research Institution: Nagoya Institute of Technology
• Principal Investigator: Tokuda Keiichi 名古屋工業大学, 工学(系)研究科(研究院), 教授 (20217483)
• Co-Investigator(Kenkyū-buntansha): 山岸 順一 国立情報学研究所, コンテンツ科学研究系, 教授 (70709352) ; 南角 吉彦 名古屋工業大学, 工学(系)研究科(研究院), 准教授 (80397497) ; 橋本 佳 名古屋工業大学, 工学(系)研究科(研究院), 准教授 (10635907)
• Project Period (FY): 2018-04-01 – 2022-03-31
• Project Status: Completed (Fiscal Year 2021)
• Budget Amount: ¥44,070,000 (Direct Cost: ¥33,900,000、Indirect Cost: ¥10,170,000); Fiscal Year 2021: ¥8,580,000 (Direct Cost: ¥6,600,000、Indirect Cost: ¥1,980,000); Fiscal Year 2020: ¥10,270,000 (Direct Cost: ¥7,900,000、Indirect Cost: ¥2,370,000); Fiscal Year 2019: ¥11,180,000 (Direct Cost: ¥8,600,000、Indirect Cost: ¥2,580,000); Fiscal Year 2018: ¥14,040,000 (Direct Cost: ¥10,800,000、Indirect Cost: ¥3,240,000)
• Keywords: 音声プライバシー / マスキング / 音声合成 / 音声情報処理 / プライバシー技術 / プライバシー保護

Outline of Final Research Achievements

This research aims to establish a next-generation voice privacy protection technology (PRISM: PRIvacy Selecting Masking) that can selectively protect privacy information such as personal identity and speech content contained in speech. We have proposed a synthetic voice-based masking method for voice privacy protection in real space and a deep learning machine learning method for voice privacy protection in cyberspace, and have confirmed the effectiveness of each method.

Academic Significance and Societal Importance of the Research Achievements

スマートスピーカーなどの音声を入力とするシステムの普及により，音声に含まれるプライバシー情報が収集されるといったプライバシーの侵害が懸念されている。音声には、個人の特定だけでなく、年齢や性別、発話内容など、様々なプライバシー情報が含まれているが、本研究で確立した選択的音声プライバシー保護技術によれば、場所や状況、発話内容等に応じ、それぞれに適した形で音声プライバシー情報を保護することが可能となり、今後のネットワーク化された情報社会において、安心して音声インタフェースを利用することが可能となる。

Research Products

• [Int'l Joint Research] エジンバラ大学(英国)
• [Int'l Joint Research] Eurecom/INRIA（フランス国立情報学自動制御研究所）/アヴィニョン大学(フランス)
• [Int'l Joint Research] 国立情報学自動制御研究所 (INRIA)/Eurecom研究所/アビニョン大学(フランス)
• [Int'l Joint Research] エジンバラ大学/シェフィールド大学(英国)
• [Int'l Joint Research] 国立情報学自動制御研究所 (INRIA)/Eurecom研究所/アビニョン大学(フランス)
• [Int'l Joint Research] エジンバラ大学/シェフィールド大学(英国)
• [Journal Article] The VoicePrivacy 2020 Challenge: Results and findings (2022)
  • Author(s): Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Jose Patino, Brij Mohan Lal Srivastava, Paul-Gauthier No?, Andreas Nautsch, Nicholas Evans, Junichi Yamagishi, Benjamin O’Brien, Ana?s Chanclu, Jean-Fran?ois Bonastre, Massimiliano Todisco, Mohamed Maouche
  • Journal Title: Computer Speech & Language Volume: 74 Pages: 101362-101362
  • DOI: 10.1016/j.csl.2022.101362
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System (2021)
  • Author(s): Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Journal Title: IEEE/ACM Transactions on Audio, Speech and Language Processing Volume: 29 Pages: 2803-2815
  • DOI: 10.1109/taslp.2021.3104165
  • Peer Reviewed / Open Access
• [Journal Article] PeriodNet: A Non-Autoregressive Raw Waveform Generative Model With a Structure Separating Periodic and Aperiodic Components (2021)
  • Author(s): Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Journal Title: IEEE Access Volume: 9 Pages: 137599-137612
  • DOI: 10.1109/access.2021.3118033
  • Peer Reviewed / Open Access
• [Journal Article] Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis (2020)
  • Author(s): Wang Xin、Takaki Shinji、Yamagishi Junichi
  • Journal Title: IEEE/ACM Transactions on Audio, Speech, and Language Processing Volume: 28 Pages: 402-415
  • DOI: 10.1109/taslp.2019.2956145
  • Peer Reviewed / Open Access
• [Journal Article] A vector quantized variational autoencoder (VQ-VAE) autoregressive neural F0 model for statistical parametric speech synthesis (2019)
  • Author(s): Xin Wang, Shinji Takaki, Junichi Yamagishi, Simon King, and Keiichi Tokuda
  • Journal Title: IEEE/ACM Transactions on Audio, Speech and Language Processing Volume: 28 Pages: 157-170
  • DOI: 10.1109/taslp.2019.2950099
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Wasserstein GAN and waveform loss-based acoustic model training for multi-speaker text-to-speech synthesis systems using a WaveNet neural vocoder (2018)
  • Author(s): Yi Zhao, Shinji Takaki, Hieu-Thi Luong, Junichi Yamagishi, Daisuke Saito, and Nobuaki Minematsu
  • Journal Title: IEEE Access Volume: 6 Pages: 60478-60488
  • DOI: 10.1109/access.2018.2872060
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Presentation] 深層学習に基づく音声合成における顔画像情報を用いたクロスモーダル話者適応 (2022)
  • Author(s): 平光啓祐, 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2022年春季研究発表会
• [Presentation] 声質・声の高さ・話速を変更可能なニューラルボコーダ構成法の検討 (2022)
  • Author(s): 佐々木一匡, 吉村建慶, 高木信二, 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2022年春季研究発表会
• [Presentation] HSMM構造化アテンションに基づく音声合成のためのメモリ削減手法 (2022)
  • Author(s): 藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2022年春季研究発表会
• [Presentation] 非周期性指標を考慮したニューラルボコーダの学習 (2022)
  • Author(s): 法野行哉, 高木信二, 橋本佳, 中村和寛, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2022年春季研究発表会
• [Presentation] Autoregressive variational autoencoder with a hidden semi-Markov model-based structured attention for speech synthesis (2022)
  • Author(s): Takato Fujimoto, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components (2021)
  • Author(s): Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] 因子分析に基づくHSMMを利用した構造化アテンション音声合成 (2021)
  • Author(s): 高木信二, 牛田光一, 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2021年秋季研究発表会
• [Presentation] DNN歌声合成のための調子はずれ補正 (2021)
  • Author(s): 法野行哉, 橋本佳, 大浦圭一郎,南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2021年秋季研究発表会
• [Presentation] 発声タイミングのずれを考慮したsequence-to-sequence歌声合成 (2021)
  • Author(s): 法野行哉, 加藤大誠, 橋本佳, 大浦圭一郎,南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2021年秋季研究発表会
• [Presentation] 隠れセミマルコフモデルによる構造化アテンションを用いた自己回帰型VAEに基づくsequence-to-sequence音声合成 (2021)
  • Author(s): 藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2021年秋季研究発表会
• [Presentation] Exploring Disentanglement with Multilingual and Monolingual VQ-VAE (2021)
  • Author(s): Jennifer Williams, Jason Fong, Erica Cooper, Junichi Yamagishi
  • Organizer: Speech Synthesis Workshop 2021 (SSW11)
  • Int'l Joint Research
• [Presentation] Revisiting Speech Content Privacy (2021)
  • Author(s): Jennifer Williams, Junichi Yamagishi, Paul-Gauthier Noe, Cassia Valentini Botinhao, Jean-Francois Bonastre
  • Organizer: ISCA Security and Privacy in Speech Communication 2021 (1st SPSC Symposium)
  • Int'l Joint Research
• [Presentation] 学習時と合成時の一貫性を考慮したVAEに基づく自己回帰型sequence-to-sequence音声合成 (2021)
  • Author(s): 藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2021年春季研究発表会
• [Presentation] 隠れセミマルコフモデルに基づく構造化アテンションを用いたSequence-to-Sequence音声合成 (2021)
  • Author(s): 角谷健太, 吉村建慶, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2021年春季研究発表会
• [Presentation] 周期・非周期成分の分離に基づくニューラルボコーダによる音声波形のモデル化の検討 (2021)
  • Author(s): 法野行哉, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2021年春季研究発表会
• [Presentation] 勾配ブースティング決定木を用いた音声合成手法の検討 (2021)
  • Author(s): 岩田康平, 高木信二, 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2021年春季研究発表会
• [Presentation] 深層学習に基づく音声合成における顔画像を用いた話者適応 (2020)
  • Author(s): 平光啓祐，橋本佳，徳田恵一，南角吉彦
  • Organizer: 第18回情報学ワークショップ
• [Presentation] 生成モデルの構造を組み込んだ系列変分オートエンコーダに基づく話者認識 (2020)
  • Author(s): 車田智哉，木下耕介，吉村建慶，橋本佳，南角吉彦，徳田恵一
  • Organizer: 第18回情報学ワークショップ
• [Presentation] 出力遅延を考慮したアテンション機構に基づくリアルタイム声質変換 (2020)
  • Author(s): 西村愛理，藤本崇人，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
  • Organizer: 第18回情報学ワークショップ
• [Presentation] 音声合成における特徴的な発話スタイルの転移学習 (2020)
  • Author(s): 久野宏彰，高木信二，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
  • Organizer: 第18回情報学ワークショップ
• [Presentation] ニューラルボコーダを用いた音声符号化手法の検討 (2020)
  • Author(s): 成田哲郎，吉村建慶，橋本佳，南角吉彦，徳田恵一
  • Organizer: 第18回情報学ワークショップ
• [Presentation] 音声合成における敵対的生成ネットワークを用いた複数言語・複数話者モデリングの検討 (2020)
  • Author(s): 大谷眞史，佐藤優介，高木信二，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
  • Organizer: 第18回情報学ワークショップ
• [Presentation] 大規模音楽データを活用した汎用WaveNetボコーダ構成法の検討 (2020)
  • Author(s): 佐々木一匡，吉村建慶，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
  • Organizer: 第18回情報学ワークショップ
• [Presentation] 音声プライバシー保護のためのノンパラレル声質変換による話者匿名化の検討 (2020)
  • Author(s): 厚地俊哉，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
  • Organizer: 第18回情報学ワークショップ
• [Presentation] 勾配ブースティング決定木を用いた高速な音声合成手法の検討 (2020)
  • Author(s): 岩田康平，高木信二，橋本佳，南角吉彦，徳田恵一
  • Organizer: 第18回情報学ワークショップ
• [Presentation] 深層学習に基づく楽器音合成における音響モデルの比較検討 (2020)
  • Author(s): 前川遼太朗，高木信二，橋本佳，大浦圭一郎，南角吉彦, 徳田恵一
  • Organizer: 第18回情報学ワークショップ
• [Presentation] Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis (2020)
  • Author(s): Yukiya Hono, Kazuna Tsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: Interspeech 2020
  • Int'l Joint Research
• [Presentation] Design Choices for X-Vector Based Speaker Anonymization (2020)
  • Author(s): Brij Mohan Lal Srivastava, Natalia Tomashenko, Xin Wang, Emmanuel Vincent, Junichi Yamagishi, Mohamed Maouche, Aur?lien Bellet, Marc Tommasi
  • Organizer: Interspeech 2020
  • Int'l Joint Research
• [Presentation] Introducing the VoicePrivacy Initiative (2020)
  • Author(s): Natalia Tomashenko, Brij Mohan Lal Srivastava, Xin Wang, Emmanuel Vincent, Andreas Nautsch, Junichi Yamagishi, Nicholas Evans, Jose Patino, Jean-Fran?ois Bonastre, Paul-Gauthier No?, Massimiliano Todisco
  • Organizer: Interspeech 2020
  • Int'l Joint Research
• [Presentation] The Privacy ZEBRA: Zero Evidence Biometric Recognition Assessment (2020)
  • Author(s): Andreas Nautsch, Jose Patino, N. Tomashenko, Junichi Yamagishi, Paul-Gauthier No?, Jean-Fran?ois Bonastre, Massimiliano Todisco, Nicholas Evans
  • Organizer: Interspeech 2020
  • Int'l Joint Research
• [Presentation] 感情音声合成のためのDirichlet VAE (2020)
  • Author(s): 藤本崇人, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2020年秋季研究発表会
• [Presentation] DNNに基づく音声ボコーダにおける周期・非周期成分のモデル化の検討 (2020)
  • Author(s): 法野行哉, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2020年秋季研究発表会
• [Presentation] 音声合成における敵対的生成ネットワークを用いた複数言語・複数話者モデリング (2020)
  • Author(s): 大谷眞史, 佐藤優介, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2020年秋季研究発表会
• [Presentation] Semi-supervised learning based on hierarchical generative models for end-to-end speech synthesis (2020)
  • Author(s): Takato Fujimoto, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] End-to-End音声合成のための階層化生成モデルに基づく半教師あり学習 (2020)
  • Author(s): 藤本崇人, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2020年春季研究発表会
• [Presentation] 楽譜時間情報を用いたアテンション機構に基づく歌声合成の検討 (2019)
  • Author(s): 村田舜馬, 藤本崇人, 法野行哉, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2019年秋季研究発表会
• [Presentation] Audiovisual speaker conversion: jointly and simultaneously transforming facial expression and acoustic characteristics (2019)
  • Author(s): Fuming Fang, Xin Wang, Junichi Yamagishi, Isao Echizen
  • Organizer: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] Waveform generation for text-to-speech synthesis using pitch-synchronous multi-scale generative adversarial networks (2019)
  • Author(s): Lauri Juvela, Bajibabu Bollepalli, Junichi Yamagishi, Paavo Alku
  • Organizer: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language (2019)
  • Author(s): Yusuke Yasuda, Xin Wang, Shinji Takaki, Junichi Yamagishi
  • Organizer: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] Neural source-filter-based waveform model for statistical parametric speech synthesis (2019)
  • Author(s): Xin Wang, Shinji Takaki, Junichi Yamagishi
  • Organizer: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] STFT spectral loss for training a neural speech waveform model (2019)
  • Author(s): Shinji Takaki, Toru Nakashika, Xin Wang, Junichi Yamagishi
  • Organizer: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] 周期・非周期信号を用いたDNNに基づくリアルタイム音声ボコーダ (2019)
  • Author(s): 大浦圭一郎, 中村和寛, 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 情報処理学会研究報告
• [Presentation] 周期・非周期信号を用いた敵対的生成ネットワークに基づくリアルタイム音声ボコーダ (2019)
  • Author(s): 大浦圭一郎, 高木信二, 中村和寛, 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2019年秋季研究発表会
• [Presentation] Statistical approach to speech synthesis: past, present and future (2019)
  • Author(s): Keiichi Tokuda
  • Organizer: Interspeech 2019
  • Int'l Joint Research / Invited
• [Presentation] GELP: GAN-Excited Liner Prediction for Speech Synthesis from Mel-spectrogram (2019)
  • Author(s): Lauri Juvela, Bajibabu Bollepalli, Junichi Yamagishi, Paavo Alku
  • Organizer: Interspeech 2019
  • Int'l Joint Research
• [Presentation] Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet (2019)
  • Author(s): Mingyang Zhang, Xin Wang, Fuming Fang, Haizhou Li, Junichi Yamagishi
  • Organizer: Interspeech 2019
  • Int'l Joint Research
• [Presentation] Deep neural network based real-time speech vocoder with periodic and aperiodic inputs (2019)
  • Author(s): Keiichiro Oura, Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: 10th ISCA Speech Synthesis Workshop (SSW10)
  • Int'l Joint Research
• [Presentation] Impacts of input linguistic feature representation on Japanese end-to-end speech synthesis (2019)
  • Author(s): Takato Fujimoto, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: 10th ISCA Speech Synthesis Workshop (SSW10)
  • Int'l Joint Research
• [Presentation] Low computational cost speech synthesis based on deep neural networks using hidden semi-Markov model structures (2019)
  • Author(s): Motoki Shimada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: 10th ISCA Speech Synthesis Workshop (SSW10)
  • Int'l Joint Research
• [Presentation] Speaker Anonymization Using X-vector and Neural Waveform Models (2019)
  • Author(s): Fuming Fang, Xin Wang, Junichi Yamagishi, Isao Echizen, Massimiliano Todisco, Nicholas Evans,Jean-Francois Bonastre
  • Organizer: 10th ISCA Speech Synthesis Workshop (SSW10)
  • Int'l Joint Research
• [Presentation] Initial investigation of encoder-decoder end-to-end TTS using marginalization of monotonic hard alignments (2019)
  • Author(s): Yusuke Yasuda, Xin Wang, Junichi Yamagishi
  • Organizer: 10th ISCA Speech Synthesis Workshop (SSW10)
  • Int'l Joint Research
• [Presentation] Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis (2019)
  • Author(s): Xin Wang, Junichi Yamagishi
  • Organizer: 10th ISCA Speech Synthesis Workshop (SSW10)
  • Int'l Joint Research
• [Presentation] 統計的音声合成の進展と展望 (2019)
  • Author(s): 徳田恵一
  • Organizer: 音声研究会
  • Invited
• [Presentation] 公共空間におけるスピーチプライバシー保護を目的とした合成音声によるサウンドマスキングの検討 (2019)
  • Author(s): 次井貴浩, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 音声研究会
• [Presentation] 歌声合成におけるニューラルボコーダの比較検討 (2019)
  • Author(s): 和田蒼汰, 法野行哉, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 音声研究会
• [Presentation] BOOTSTRAPPING NON-PARALLEL VOICE CONVERSION FROM SPEAKER-ADAPTIVE TEXT-TO-SPEECH (2019)
  • Author(s): Hieu-Thi Luong, Junichi Yamagishi
  • Organizer: IEEE ASRU 2019
  • Int'l Joint Research
• [Presentation] 隠れセミマルコフモデルの構造を用いたDNNに基づく音声合成における計算量削減手法の検討 (2019)
  • Author(s): 島田基樹, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2019年春季研究発表会
• [Presentation] 周期・非周期信号から駆動するディープニューラルネットワークに基づく音声ボコーダ (2019)
  • Author(s): 藤本崇人, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2019年春季研究発表会
• [Presentation] 敵対的生成ネットワークを用いた歌声合成の検討 (2019)
  • Author(s): 法野行哉, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2019年春季研究発表会
• [Presentation] DNNに基づく感情音声合成のための敵対的学習の検討 (2019)
  • Author(s): 角谷健太, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2019年春季研究発表会
• [Presentation] Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos (2019)
  • Author(s): Huy H. Nguyen, Junichi Yamagishi, Isao Echizen
  • Organizer: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] Singing voice synthesis based on generative adversarial networks (2019)
  • Author(s): Yukiya Hono, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
  • Int'l Joint Research
• [Presentation] Singing Voice Conversion Using Posted Waveform Data on Music Social Media (2018)
  • Author(s): Koki Senda, Yukiya Hono, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2018)
  • Int'l Joint Research
• [Presentation] Recent Development of the DNN-based Singing Voice Synthesis System -- Sinsy (2018)
  • Author(s): Yukiya Hono, Shumma Murata, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2018)
  • Int'l Joint Research
• [Presentation] Speech Synthesis Using WaveNet Vocoder Based on Periodic/Aperiodic Decomposition (2018)
  • Author(s): Takato Fujimoto, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2018)
  • Int'l Joint Research
• [Presentation] Speaker Adaptation for Speech Synthesis Based on Deep Neural Networks Using Hidden Semi-Markov Model Structures (2018)
  • Author(s): Kento Nakao, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2018)
  • Int'l Joint Research
• [Presentation] Discriminative feature extraction based on sequential variational autoencoder for speaker recognition (2018)
  • Author(s): Takenori Yoshimura, Natsumi Koike, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2018)
  • Int'l Joint Research
• [Presentation] The NITech text-to-speech system for the Blizzard Challenge 2018 (2018)
  • Author(s): Kei Sawada, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
  • Organizer: Blizzard Challenge 2018 Workshop
  • Int'l Joint Research
• [Presentation] 時間構造を考慮したニューラルネットワークに基づく音声合成における話者適応の検討 (2018)
  • Author(s): 中尾健人, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 音声研究会
• [Presentation] 話者認識のためのSequential VAEに基づく特徴抽出の検討 (2018)
  • Author(s): 吉村建慶, 小池なつみ, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2018年秋季研究発表会
• [Presentation] 公共空間におけるスマートデバイスを用いた音声入力のためのサウンドマスキングに関する検討 (2018)
  • Author(s): 次井貴浩, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2018年秋季研究発表会
• [Presentation] 周期・非周期成分の分離に基づくWaveNetボコーダを用いた音声合成 (2018)
  • Author(s): 藤本崇人, 吉村建慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2018年秋季研究発表会
• [Presentation] Deep Neural Networkに基づく歌声合成システム -- Sinsy (2018)
  • Author(s): 法野行哉, 村田舜馬, 中村和寛, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2018年秋季研究発表会
• [Presentation] Blizzard Challenge 2018のためのNITechテキスト音声合成システム (2018)
  • Author(s): 沢田慶, 吉村建慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会2018年秋季研究発表会
• [Presentation] Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems (2018)
  • Author(s): Fuming Fang, Junichi Yamagishi, Isao Echizen, Md Sahidullah, Tomi Kinnunen
  • Organizer: WIFS2018: IEEE International Workshop on Information Forensics and Security
  • Int'l Joint Research
• [Presentation] Scaling and bias codes for modeling speaker-adaptive DNN-based speech synthesis systems (2018)
  • Author(s): Hieu-Thi Luong, Junichi Yamagishi
  • Organizer: 2018 IEEE Workshop on Spoken Language Technology (SLT 2018)
  • Int'l Joint Research
• [Remarks] Voice Privacy Challenge
  • URL: https://www.voiceprivacychallenge.org/
• [Remarks] VoicePrivacy initiative
  • URL: https://www.voiceprivacychallenge.org/
• [Remarks] Baseline Recipe for VoicePrivacy Challenge 2020
  • URL: https://github.com/Voice-Privacy-Challenge/Voice-Privacy-Challenge-2020
• [Funded Workshop] Voice Privacy Challenge (https://www.voiceprivacychallenge.org/) (2020)