Suche senden
Hochladen
声質変換の概要と最新手法の紹介
•
6 gefällt mir
•
2,651 views
K
Kentaro Tachibana
Folgen
声質変換の概要とCycleGANを用いたparallel data free声質変換、VQ-VAEの説明資料。
Weniger lesen
Mehr lesen
Wissenschaft
Melden
Teilen
Melden
Teilen
1 von 35
Jetzt herunterladen
Downloaden Sie, um offline zu lesen
Empfohlen
差分スペクトル法に基づく DNN 声質変換の計算量削減に向けたフィルタ推定
差分スペクトル法に基づく DNN 声質変換の計算量削減に向けたフィルタ推定
Shinnosuke Takamichi
異常音検知に対する深層学習適用事例
異常音検知に対する深層学習適用事例
NU_I_TODALAB
JVS:フリーの日本語多数話者音声コーパス
JVS:フリーの日本語多数話者音声コーパス
Shinnosuke Takamichi
音響信号に対する異常音検知技術と応用
音響信号に対する異常音検知技術と応用
Yuma Koizumi
統計的手法に基づく異常音検知の理論と応用
統計的手法に基づく異常音検知の理論と応用
Yuma Koizumi
ICASSP 2019での音響信号処理分野の世界動向
ICASSP 2019での音響信号処理分野の世界動向
Yuma Koizumi
音声合成のコーパスをつくろう
音声合成のコーパスをつくろう
Shinnosuke Takamichi
Interspeech2022 参加報告
Interspeech2022 参加報告
Yuki Saito
Empfohlen
差分スペクトル法に基づく DNN 声質変換の計算量削減に向けたフィルタ推定
差分スペクトル法に基づく DNN 声質変換の計算量削減に向けたフィルタ推定
Shinnosuke Takamichi
異常音検知に対する深層学習適用事例
異常音検知に対する深層学習適用事例
NU_I_TODALAB
JVS:フリーの日本語多数話者音声コーパス
JVS:フリーの日本語多数話者音声コーパス
Shinnosuke Takamichi
音響信号に対する異常音検知技術と応用
音響信号に対する異常音検知技術と応用
Yuma Koizumi
統計的手法に基づく異常音検知の理論と応用
統計的手法に基づく異常音検知の理論と応用
Yuma Koizumi
ICASSP 2019での音響信号処理分野の世界動向
ICASSP 2019での音響信号処理分野の世界動向
Yuma Koizumi
音声合成のコーパスをつくろう
音声合成のコーパスをつくろう
Shinnosuke Takamichi
Interspeech2022 参加報告
Interspeech2022 参加報告
Yuki Saito
[DL輪読会]Diffusion-based Voice Conversion with Fast Maximum Likelihood Samplin...
[DL輪読会]Diffusion-based Voice Conversion with Fast Maximum Likelihood Samplin...
Deep Learning JP
[DL輪読会]Wavenet a generative model for raw audio
[DL輪読会]Wavenet a generative model for raw audio
Deep Learning JP
Neural text-to-speech and voice conversion
Neural text-to-speech and voice conversion
Yuki Saito
A Method of Speech Waveform Synthesis based on WaveNet considering Speech Gen...
A Method of Speech Waveform Synthesis based on WaveNet considering Speech Gen...
Akira Tamamori
Fisher Vectorによる画像認識
Fisher Vectorによる画像認識
Takao Yamanaka
論文紹介 wav2vec: Unsupervised Pre-training for Speech Recognition
論文紹介 wav2vec: Unsupervised Pre-training for Speech Recognition
YosukeKashiwagi1
深層学習を利用した音声強調
深層学習を利用した音声強調
Yuma Koizumi
Skip Connection まとめ(Neural Network)
Skip Connection まとめ(Neural Network)
Yamato OKAMOTO
複数話者WaveNetボコーダに関する調査
複数話者WaveNetボコーダに関する調査
Tomoki Hayashi
[DL輪読会]Parallel WaveNet: Fast High-Fidelity Speech Synthesis
[DL輪読会]Parallel WaveNet: Fast High-Fidelity Speech Synthesis
Deep Learning JP
全体セミナーWfst
全体セミナーWfst
Jiro Nishitoba
Variational AutoEncoder
Variational AutoEncoder
Kazuki Nitta
音声感情認識の分野動向と実用化に向けたNTTの取り組み
音声感情認識の分野動向と実用化に向けたNTTの取り組み
Atsushi_Ando
[DL輪読会]Recent Advances in Autoencoder-Based Representation Learning
[DL輪読会]Recent Advances in Autoencoder-Based Representation Learning
Deep Learning JP
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
Deep Learning JP
深層生成モデルに基づく音声合成技術
深層生成モデルに基づく音声合成技術
NU_I_TODALAB
実装レベルで学ぶVQVAE
実装レベルで学ぶVQVAE
ぱんいち すみもと
深層学習と音響信号処理
深層学習と音響信号処理
Yuma Koizumi
深層学習を用いた音源定位、音源分離、クラス分類の統合~環境音セグメンテーション手法の紹介~
深層学習を用いた音源定位、音源分離、クラス分類の統合~環境音セグメンテーション手法の紹介~
Yui Sudo
[DL輪読会]Towards End-to-End Prosody Transfer for Expressive Speech Synthesis wi...
[DL輪読会]Towards End-to-End Prosody Transfer for Expressive Speech Synthesis wi...
Deep Learning JP
CODE FESTIVAL 2015 予選A 解説
CODE FESTIVAL 2015 予選A 解説
AtCoder Inc.
Gadgteteer clean code
Gadgteteer clean code
Eric De Carufel
Weitere ähnliche Inhalte
Was ist angesagt?
[DL輪読会]Diffusion-based Voice Conversion with Fast Maximum Likelihood Samplin...
[DL輪読会]Diffusion-based Voice Conversion with Fast Maximum Likelihood Samplin...
Deep Learning JP
[DL輪読会]Wavenet a generative model for raw audio
[DL輪読会]Wavenet a generative model for raw audio
Deep Learning JP
Neural text-to-speech and voice conversion
Neural text-to-speech and voice conversion
Yuki Saito
A Method of Speech Waveform Synthesis based on WaveNet considering Speech Gen...
A Method of Speech Waveform Synthesis based on WaveNet considering Speech Gen...
Akira Tamamori
Fisher Vectorによる画像認識
Fisher Vectorによる画像認識
Takao Yamanaka
論文紹介 wav2vec: Unsupervised Pre-training for Speech Recognition
論文紹介 wav2vec: Unsupervised Pre-training for Speech Recognition
YosukeKashiwagi1
深層学習を利用した音声強調
深層学習を利用した音声強調
Yuma Koizumi
Skip Connection まとめ(Neural Network)
Skip Connection まとめ(Neural Network)
Yamato OKAMOTO
複数話者WaveNetボコーダに関する調査
複数話者WaveNetボコーダに関する調査
Tomoki Hayashi
[DL輪読会]Parallel WaveNet: Fast High-Fidelity Speech Synthesis
[DL輪読会]Parallel WaveNet: Fast High-Fidelity Speech Synthesis
Deep Learning JP
全体セミナーWfst
全体セミナーWfst
Jiro Nishitoba
Variational AutoEncoder
Variational AutoEncoder
Kazuki Nitta
音声感情認識の分野動向と実用化に向けたNTTの取り組み
音声感情認識の分野動向と実用化に向けたNTTの取り組み
Atsushi_Ando
[DL輪読会]Recent Advances in Autoencoder-Based Representation Learning
[DL輪読会]Recent Advances in Autoencoder-Based Representation Learning
Deep Learning JP
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
Deep Learning JP
深層生成モデルに基づく音声合成技術
深層生成モデルに基づく音声合成技術
NU_I_TODALAB
実装レベルで学ぶVQVAE
実装レベルで学ぶVQVAE
ぱんいち すみもと
深層学習と音響信号処理
深層学習と音響信号処理
Yuma Koizumi
深層学習を用いた音源定位、音源分離、クラス分類の統合~環境音セグメンテーション手法の紹介~
深層学習を用いた音源定位、音源分離、クラス分類の統合~環境音セグメンテーション手法の紹介~
Yui Sudo
[DL輪読会]Towards End-to-End Prosody Transfer for Expressive Speech Synthesis wi...
[DL輪読会]Towards End-to-End Prosody Transfer for Expressive Speech Synthesis wi...
Deep Learning JP
Was ist angesagt?
(20)
[DL輪読会]Diffusion-based Voice Conversion with Fast Maximum Likelihood Samplin...
[DL輪読会]Diffusion-based Voice Conversion with Fast Maximum Likelihood Samplin...
[DL輪読会]Wavenet a generative model for raw audio
[DL輪読会]Wavenet a generative model for raw audio
Neural text-to-speech and voice conversion
Neural text-to-speech and voice conversion
A Method of Speech Waveform Synthesis based on WaveNet considering Speech Gen...
A Method of Speech Waveform Synthesis based on WaveNet considering Speech Gen...
Fisher Vectorによる画像認識
Fisher Vectorによる画像認識
論文紹介 wav2vec: Unsupervised Pre-training for Speech Recognition
論文紹介 wav2vec: Unsupervised Pre-training for Speech Recognition
深層学習を利用した音声強調
深層学習を利用した音声強調
Skip Connection まとめ(Neural Network)
Skip Connection まとめ(Neural Network)
複数話者WaveNetボコーダに関する調査
複数話者WaveNetボコーダに関する調査
[DL輪読会]Parallel WaveNet: Fast High-Fidelity Speech Synthesis
[DL輪読会]Parallel WaveNet: Fast High-Fidelity Speech Synthesis
全体セミナーWfst
全体セミナーWfst
Variational AutoEncoder
Variational AutoEncoder
音声感情認識の分野動向と実用化に向けたNTTの取り組み
音声感情認識の分野動向と実用化に向けたNTTの取り組み
[DL輪読会]Recent Advances in Autoencoder-Based Representation Learning
[DL輪読会]Recent Advances in Autoencoder-Based Representation Learning
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
[DL輪読会]NVAE: A Deep Hierarchical Variational Autoencoder
深層生成モデルに基づく音声合成技術
深層生成モデルに基づく音声合成技術
実装レベルで学ぶVQVAE
実装レベルで学ぶVQVAE
深層学習と音響信号処理
深層学習と音響信号処理
深層学習を用いた音源定位、音源分離、クラス分類の統合~環境音セグメンテーション手法の紹介~
深層学習を用いた音源定位、音源分離、クラス分類の統合~環境音セグメンテーション手法の紹介~
[DL輪読会]Towards End-to-End Prosody Transfer for Expressive Speech Synthesis wi...
[DL輪読会]Towards End-to-End Prosody Transfer for Expressive Speech Synthesis wi...
Ähnlich wie 声質変換の概要と最新手法の紹介
CODE FESTIVAL 2015 予選A 解説
CODE FESTIVAL 2015 予選A 解説
AtCoder Inc.
Gadgteteer clean code
Gadgteteer clean code
Eric De Carufel
Orb における Cassandra への取り組み
Orb における Cassandra への取り組み
Orb, Inc.
0.47 inch LCD Micro Dispalay 800x600 Resolution RGB Interface LCD Screen
0.47 inch LCD Micro Dispalay 800x600 Resolution RGB Interface LCD Screen
Shawn Lee
20170322_ICON21技術セミナー1_加藤
20170322_ICON21技術セミナー1_加藤
ICT_CONNECT_21
Attention-Based Adaptive Selection of Operations for Image Restoration in the...
Attention-Based Adaptive Selection of Operations for Image Restoration in the...
MasanoriSuganuma
stackconf 2022: Are all programming languages in english?
stackconf 2022: Are all programming languages in english?
NETWAYS
Tensorflow and python : fault detection system - PyCon Taiwan 2017
Tensorflow and python : fault detection system - PyCon Taiwan 2017
Eric Ahn
2937
2937
kluexamcell
Hong.bas
Hong.bas
Donald Stevens
Hong.bas
Hong.bas
Donald Stevens
Linear Algebra Previous Year Questions of Csir Net Mathematical Science and t...
Linear Algebra Previous Year Questions of Csir Net Mathematical Science and t...
Santoshi Family
Introduction to Artificial Neural Networks (ANNs) - Step-by-Step Training & T...
Introduction to Artificial Neural Networks (ANNs) - Step-by-Step Training & T...
Ahmed Gad
Salesforce Big Object 最前線
Salesforce Big Object 最前線
Salesforce Developers Japan
【ECCV 2018】CornerNet: Detecting Objects as Paired Keypoints
【ECCV 2018】CornerNet: Detecting Objects as Paired Keypoints
cvpaper. challenge
Safe Reinforcement Learning
Safe Reinforcement Learning
Dongmin Lee
Stargz Snapshotter: イメージのpullを省略してcontainerdでコンテナを高速に起動する
Stargz Snapshotter: イメージのpullを省略してcontainerdでコンテナを高速に起動する
Kohei Tokunaga
Systems and methods for visual presentation and selection of ivr menu
Systems and methods for visual presentation and selection of ivr menu
Tal Lavian Ph.D.
Project management
Project management
Anurag Srivastava
FIWARE Global Summit - Smart City / Community Services and Infrastructures
FIWARE Global Summit - Smart City / Community Services and Infrastructures
FIWARE
Ähnlich wie 声質変換の概要と最新手法の紹介
(20)
CODE FESTIVAL 2015 予選A 解説
CODE FESTIVAL 2015 予選A 解説
Gadgteteer clean code
Gadgteteer clean code
Orb における Cassandra への取り組み
Orb における Cassandra への取り組み
0.47 inch LCD Micro Dispalay 800x600 Resolution RGB Interface LCD Screen
0.47 inch LCD Micro Dispalay 800x600 Resolution RGB Interface LCD Screen
20170322_ICON21技術セミナー1_加藤
20170322_ICON21技術セミナー1_加藤
Attention-Based Adaptive Selection of Operations for Image Restoration in the...
Attention-Based Adaptive Selection of Operations for Image Restoration in the...
stackconf 2022: Are all programming languages in english?
stackconf 2022: Are all programming languages in english?
Tensorflow and python : fault detection system - PyCon Taiwan 2017
Tensorflow and python : fault detection system - PyCon Taiwan 2017
2937
2937
Hong.bas
Hong.bas
Hong.bas
Hong.bas
Linear Algebra Previous Year Questions of Csir Net Mathematical Science and t...
Linear Algebra Previous Year Questions of Csir Net Mathematical Science and t...
Introduction to Artificial Neural Networks (ANNs) - Step-by-Step Training & T...
Introduction to Artificial Neural Networks (ANNs) - Step-by-Step Training & T...
Salesforce Big Object 最前線
Salesforce Big Object 最前線
【ECCV 2018】CornerNet: Detecting Objects as Paired Keypoints
【ECCV 2018】CornerNet: Detecting Objects as Paired Keypoints
Safe Reinforcement Learning
Safe Reinforcement Learning
Stargz Snapshotter: イメージのpullを省略してcontainerdでコンテナを高速に起動する
Stargz Snapshotter: イメージのpullを省略してcontainerdでコンテナを高速に起動する
Systems and methods for visual presentation and selection of ivr menu
Systems and methods for visual presentation and selection of ivr menu
Project management
Project management
FIWARE Global Summit - Smart City / Community Services and Infrastructures
FIWARE Global Summit - Smart City / Community Services and Infrastructures
Mehr von Kentaro Tachibana
ICASSP2020音声&音響読み会Mellotron
ICASSP2020音声&音響読み会Mellotron
Kentaro Tachibana
Interspeech2019読み会 音声生成
Interspeech2019読み会 音声生成
Kentaro Tachibana
190910 SHIBUYA synapse
190910 SHIBUYA synapse
Kentaro Tachibana
ICASSP2019 音声&音響読み会 テーマ発表音声生成
ICASSP2019 音声&音響読み会 テーマ発表音声生成
Kentaro Tachibana
Icml2018読み会_overview&GANs
Icml2018読み会_overview&GANs
Kentaro Tachibana
Icassp2018 発表参加報告 FFTNet, Tactron2紹介
Icassp2018 発表参加報告 FFTNet, Tactron2紹介
Kentaro Tachibana
Mehr von Kentaro Tachibana
(6)
ICASSP2020音声&音響読み会Mellotron
ICASSP2020音声&音響読み会Mellotron
Interspeech2019読み会 音声生成
Interspeech2019読み会 音声生成
190910 SHIBUYA synapse
190910 SHIBUYA synapse
ICASSP2019 音声&音響読み会 テーマ発表音声生成
ICASSP2019 音声&音響読み会 テーマ発表音声生成
Icml2018読み会_overview&GANs
Icml2018読み会_overview&GANs
Icassp2018 発表参加報告 FFTNet, Tactron2紹介
Icassp2018 発表参加報告 FFTNet, Tactron2紹介
Kürzlich hochgeladen
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
priyankatabhane
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
Nandakishor Bhaurao Deshmukh
Microteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical Engineering
Prajakta Shinde
Call Girls in Majnu Ka Tilla Delhi 🔝9711014705🔝 Genuine
Call Girls in Majnu Ka Tilla Delhi 🔝9711014705🔝 Genuine
thapagita
Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...
navyadasi1992
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024
AyushiRastogi48
Pests of Bengal gram_Identification_Dr.UPR.pdf
Pests of Bengal gram_Identification_Dr.UPR.pdf
PirithiRaju
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
malonesandreagweneth
GenBio2 - Lesson 1 - Introduction to Genetics.pptx
GenBio2 - Lesson 1 - Introduction to Genetics.pptx
BerniceCayabyab1
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
Columbia Weather Systems
OECD bibliometric indicators: Selected highlights, April 2024
OECD bibliometric indicators: Selected highlights, April 2024
innovationoecd
basic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomy
DrAnita Sharma
Forensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptx
kumarsanjai28051
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
maryFF1
preservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptx
noordubaliya2003
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
soniya singh
User Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather Station
Columbia Weather Systems
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
lizamodels9
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
Dole Philippines School
The dark energy paradox leads to a new structure of spacetime.pptx
The dark energy paradox leads to a new structure of spacetime.pptx
Eran Akiva Sinbar
Kürzlich hochgeladen
(20)
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
Microphone- characteristics,carbon microphone, dynamic microphone.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
Microteaching on terms used in filtration .Pharmaceutical Engineering
Microteaching on terms used in filtration .Pharmaceutical Engineering
Call Girls in Majnu Ka Tilla Delhi 🔝9711014705🔝 Genuine
Call Girls in Majnu Ka Tilla Delhi 🔝9711014705🔝 Genuine
Radiation physics in Dental Radiology...
Radiation physics in Dental Radiology...
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024
Pests of Bengal gram_Identification_Dr.UPR.pdf
Pests of Bengal gram_Identification_Dr.UPR.pdf
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
LIGHT-PHENOMENA-BY-CABUALDIONALDOPANOGANCADIENTE-CONDEZA (1).pptx
GenBio2 - Lesson 1 - Introduction to Genetics.pptx
GenBio2 - Lesson 1 - Introduction to Genetics.pptx
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
User Guide: Pulsar™ Weather Station (Columbia Weather Systems)
OECD bibliometric indicators: Selected highlights, April 2024
OECD bibliometric indicators: Selected highlights, April 2024
basic entomology with insect anatomy and taxonomy
basic entomology with insect anatomy and taxonomy
Forensic limnology of diatoms by Sanjai.pptx
Forensic limnology of diatoms by Sanjai.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
ECG Graph Monitoring with AD8232 ECG Sensor & Arduino.pptx
preservation, maintanence and improvement of industrial organism.pptx
preservation, maintanence and improvement of industrial organism.pptx
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
User Guide: Magellan MX™ Weather Station
User Guide: Magellan MX™ Weather Station
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
Call Girls In Nihal Vihar Delhi ❤️8860477959 Looking Escorts In 24/7 Delhi NCR
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
ALL ABOUT MIXTURES IN GRADE 7 CLASS PPTX
The dark energy paradox leads to a new structure of spacetime.pptx
The dark energy paradox leads to a new structure of spacetime.pptx
声質変換の概要と最新手法の紹介
1.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential
2.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential n G n n n - n A C 2
3.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential n a / []eb A D a C / D 4 1 /0 , 1 6 3
4.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential n I N ) n A B B ( ( ( ( (
5.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential 5 3 0 2 . /3 0 7 3 1 . 0 0 7 3
6.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential 6 3 0 2 . /3 0 7 3 1 . 0 0 7 3 :
7.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential n A B A 7 B ( A ) ( ; F0) ( ; bap) B
8.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential 8 (F0 ) bap • → Vocoder • • STRAIGHT [Kawahara+; ’99] • WORLD [Morise+; ’16]
9.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential Vocoder 9
10.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential vocoder 10 F0bap F0bap F0bap 1 frame frame Frame
11.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential [Abe+; ’90][stylianou+; ’98] n A B 11 F0bap F0bap GMM DNN
12.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential [Abe+; ’90][stylianou+; ’98] n B 12 AF0bap AF0bap GMM DNN • F0, bap → A • F0 bap
13.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential 13 Parallel-data B A frame A B
14.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential o s e P P • 6C C E C AA 6-- ( y • 6-- K K E 2; ] p e d r aKvt 6-- ( 3 E AA A ; G • g K V P[P PN g kO • E AA A ; G P Po - A 1 70 C + )8 i h ced • nQc i h ʻ] d l ]SP • nQc 6 6 . 7 ; 2CE; + )8 14
15.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential ig l hV vNVQ] V • 3 7 7 E C 7;6 Nk 16 6 6 6Nyo • Ns V PV cK • A6 6 6 6 V i + 7 - .6 G n a N [] • n a r pdNʻ O • t V e [n 32 3 , E6 0 G 15
16.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential Voice Conversion Challenge 2016 n n 7 7 7 n 5 5 n 01 16
17.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential Results of listening tests in VCC 2016 17 cf. http://vc-challenge.org/vcc2016/summary.html
18.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential ig l hV vNVQ] V • 3 7 7 E C 7;6 Nk 16 6 6 6Nyo • Ns V PV cK • A6 6 6 6 V i + 7 - .6 G n a N [] • n a r pdNʻ O • t V e [n 32 3 , E6 0 G 18
19.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential CycleGAN [Zhu+; ’17] n 19 cf. https://junyanz.github.io/CycleGAN/
20.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential CycleGAN [Zhu+; ’17] n n Forward-inverse mapping Inverse-forward mapping GX→Y GY→X G L real/fake loss [Kaneko+; ‘17] M mapping loss
21.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential CycleGAN [Zhu+; ’17] n n 21 Forward-inverse mapping Inverse-forward mapping GX→Y adversarial loss
22.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential CycleGAN [Zhu+; ’17] n n 22 Forward-inverse mapping Inverse-forward mapping = "#~%&'(' # log,- . + "0~%&'(' 0 log 1 − ,- 34→- . GY→X adversarial loss
23.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential CycleGAN [Zhu+; ’17] n n 23 Forward-inverse mapping Inverse-forward mapping L1loss
24.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential CycleGAN [Zhu+; ’17] n n 24 Forward-inverse mapping Inverse-forward mapping λcyc 10.0
25.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential CycleGAN parallel-data-free [Kaneko+, ’17] n NG NG n C 25 CycleGAN copy A A A A A t1 t2 tTbap bap bap bap bap F0 F0 F0 F0 F0 bap bap bap bap bap F0 F0 F0 F0 F0 A A A A A t1 t2 tT
26.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential VC . 1 1 2 r • d c U R l U • c U • t pt t G l em - 1 1 a ) ( A . (1 1 ( l • y sv cG X • g I ni L UI o 26
27.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential Network architecture n . / - . / n : . / / . / / / . 27
28.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential ig l hV vNVQ] V • 3 7 7 E C 7;6 Nk 16 6 6 6Nyo • Ns V PV cK • A6 6 6 6 V i + 7 - .6 G n a N [] • n a r pdNʻ O • t V e [n 32 3 , E6 0 G 28
29.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential Variational autoencoder (VAE) [Hinton+; '06] n z 29 x Encoder qθ(z|X) Decoder pθ(X|z) z !" # $; 0, 1 Input feature Generated feature
30.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential VQ-VAE [van den Oord+, ‘17] n - -( ) E V A n 30 x Encoder p(ze(x)|x) Decoder p(x|zq(x)) ze(x) !" A A e1 e2 e3 eK zq(x) x LQ loss VQ loss Encoder loss
31.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential VQ-VAE n [van den Oord+; ’16] t v o G a r • N x h G d • λ W l lg d • l m r e 31 ! " # = % &'( ) * +&|+&-),+&-)/0, ⋯ +&-0, # λ : d lg c d , " = +(, +0, ⋯ +&-0
32.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential VQ-VAE [van den Oord+, ’17] n 32 Encoder WaveNet ze(x) e1 e2 e3 eK zq(x) id • zq(x) id • ze(x) zq(x) id • zq(x) ( ) https://avdnoord.github.io/homepage/vqvae/
33.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential VQ-VAE [van den Oord+; ‘17] n 33 Encoder WaveNet ze(x) e1 e2 e3 eK zq(x) id cf. https://www.slideshare.net/YukiSaito8/saito18sp03 • zq(x) id • ze(x) zq(x) id • zq(x) ( ) https://avdnoord.github.io/homepage/vqvae/
34.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential n A n C - 34
35.
Copyright © DeNA
Co.,Ltd. All Rights Reserved. Strictly confidential H9J J JZJ d.-I 6 9J J JZJ 7 J[]MJ 9J[][N JVM 0 MN 1 N NRPVN e N[ Z]L ]ZRVP [XNNL ZNXZN[NV J RWV[ ][RVP J XR L JMJX R N RUN OZNY]NVLa [UWW RVP JVM JV RV[ JV JVNW][ OZNY]NVLa KJ[NM 4 N ZJL RWV W[[RKTN ZWTN WO J ZNX R R N [ Z]L ]ZN RV [W]VM[ f XNNL 1WUU]VRLJ RWV , XX -, , ... H WZR[N c +I WZR[N 4 FWSWUWZR JVM 9 bJ J eD :2 J WLWMNZ KJ[NM RP Y]JTR a [XNNL [aV N[R[ [a[ NU OWZ ZNJT RUN JXXTRLJ RWV[ f 73713 ZJV[JL RWV[ WV RVOWZUJ RWV JVM [a[ NU[ WT 3.. 2 VW , XX -,, --) + H0KN . I 0KN JSJU]ZJ 9 RSJVW JVM 6 9] JKJZJ eCWRLN LWV NZ[RWV ZW]P NL WZ Y]JV RbJ RWV f , ,+ H[ aTRJVW] c.-I F aTRJVW] 1JXXh JVM 3 W]TRVN[ e1WV RV]W][ XZWKJKRTR[ RL ZJV[OWZU OWZ WRLN LWV NZ[RWV f ( ) ..- H9JVNSW ,I A 9JVNSW JVM 6 9JUNWSJ f JZJTTNT 2J J 4ZNN CWRLN 1WV NZ[RWV [RVP 1aLTN 1WV[R[ NV 0M NZ[JZRJT N WZS[ f JZER , HG ] c ,I 8 F G ] A JZS 7[WTJ JVM 0 0 3OZW[ e VXJRZNM RUJPN W RUJPN ZJV[TJ RWV ][RVP LaLTN LWV[R[ NV JM NZ[JZRJT VN WZS[ f H6RV WV c +I 5 3 6RV WV JVM JTJS ] MRVW e NM]LRVP N MRUNV[RWVJTR a WO MJ J R VN]ZJT VN WZS[ f ,-+ ) , + H JV MNV WZM c ,I 0 JV MNV WZM JVM CRVaJT[ e N]ZJT MR[LZN N ZNXZN[NV J RWV TNJZVRVP f 7V XX +( . +( - , H JV MNV WZM d +I 0 JV 2NV WZM 2RNTNUJV 6 GNV 9 RUWVaJV CRVaJT[ 0 5ZJ N[ JVM 9 9J ]SL]WPT] eDJ NVN 0 PNVNZJ R N UWMNT OWZ ZJ J]MRW f 35
Jetzt herunterladen