FloWaveNet: A Generative Flow for Raw Audio Sungwon Kim 1 , Sang-gil - PowerPoint PPT Presentation

Jul 17, 2023 •167 likes •346 views

ICML 2019 FloWaveNet: A Generative Flow for Raw Audio Sungwon Kim 1 , Sang-gil Lee 1 , Jongyoon Song 1 , Jaehyeon Kim 2 , Sungron Yoon 1,3 1 Seoul National University, 2 Kakao Corporation, 3 ASRI, INMC, Institute of Engineering Research, Seoul

ICML 2019 FloWaveNet: A Generative Flow for Raw Audio Sungwon Kim 1 , Sang-gil Lee 1 , Jongyoon Song 1 , Jaehyeon Kim 2 , Sungron Yoon 1,3 1 Seoul National University, 2 Kakao Corporation, 3 ASRI, INMC, Institute of Engineering Research, Seoul National University Poster 6/12 6:30 PM @Pacific Ballroom #2
WaveNet ) log $ % & ':) = + log $ % & , & ., ,-' https://deepmind.com/blog/wavenet-generative-model-raw-audio/
WaveNet Sequential sampling ) log $ % & ':) = + log $ % & , & ., ,-' https://deepmind.com/blog/wavenet-generative-model-raw-audio/
Previous parallel speech synthesis models Pre-trained WaveNet Inverse Autoregressive Flows (IAFs) Probability Density Distillation !" # $ % ||# ' % Oord, Aaron, et al. "Parallel WaveNet: Fast High-Fidelity Speech Synthesis." International Conference on Machine Learning . 2018.
Previous parallel speech synthesis models Pre-trained WaveNet Parallel sampling Inverse Autoregressive Flows (IAFs) Probability Density Distillation !" # $ % ||# ' % Oord, Aaron, et al. "Parallel WaveNet: Fast High-Fidelity Speech Synthesis." International Conference on Machine Learning . 2018.
Previous parallel speech synthesis models Pre-trained WaveNet Parallel sampling Inverse Autoregressive Flows (IAFs) Probability Density Distillation Power Loss Perceptual Loss + !" # $ % ||# ' % Contrastive Loss Frame Loss Oord, Aaron, et al. "Parallel WaveNet: Fast High-Fidelity Speech Synthesis." International Conference on Machine Learning . 2018.
Our Objectives • Simplify the training procedure for parallel sampling • Maintain the quality of speech samples
Our Objectives • Simplify the training procedure for parallel sampling • Maintain the quality of speech samples Flow-based generative models for raw audio!
FloWaveNet 3 3 + % , - Raw audio Gaussian Noise + log det 2, - & Training phase log $ % & ':) = log $ + , - & ':) 2&
FloWaveNet 5 5 + % , - 34 , - Raw audio Gaussian Noise + log det 2, - & Training phase log $ % & ':) = log $ + , - & ':) 2& Sampling phase 34 (6) 6 = 6 ':) ~ 5 + 6 = 8 9, ; , & = , - <
FloWaveNet 5 5 + % , - 34 , - Raw audio Gaussian Noise + log det 2, - & Training phase log $ % & ':) = log $ + , - & ':) 2& Sampling phase 34 (6) 6 = 6 ':) ~ 5 + 6 = 8 9, ; , & = , - < 34 are designed to be computed efficiently Both the transformation , - and , - à Efficient training & Parallel sampling
FloWaveNet 7 4 56 7 4 59 4 : 7 ⋅ 4 59 7 log det 3 4 56 & log $ % & ':) = log $ + , & ':) + . 3& /
Mean Opinion Scores FloWaveNet ≥ Gaussian IAF
Sampling speed FloWaveNet ≅ Gaussian IAF ≅ Parallel WaveNet >> Autoregressive WaveNet 1000s times faster
Conclusion • FloWaveNet produces high quality audio samples as well as previous distilled models. • FloWaveNet synthesizes audio samples in parallel – w/o well pre-trained WaveNet (No distillation!) – w/o auxiliary loss terms Demo page Code Poster 6/12 6:30 PM @Pacific Ballroom #2
16

Recommend

Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture

Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design Jonathan Ho*, Xi Chen*, Aravind Srinivas, Yan Duan, Pieter Abbeel Overview - Goal: likelihood-based model with Fast sampling and training -

363 views • 11 slides

Generative vs. discriminative Generative Discriminative Belief network A is more More

Generative vs. discriminative Generative Discriminative Belief network A is more More robust modular Dont need precise model Class-conditional densities are specification, so long as it is likely to be local, characteristic

1.09k views • 15 slides

Generative networks part 2: GANs 23 / 54 Recap on generative networks Generative networks provide

Generative networks part 2: GANs 23 / 54 Recap on generative networks Generative networks provide a way to sample from any distribution. 1. Sample z , where denotes an efficiently sampleable distribution (e.g., uniform or Gaussian). 2.

486 views • 47 slides

Conditional Generative Adversarial Networks (and a brief look at image-to-image translation)

Conditional Generative Adversarial Networks (and a brief look at image-to-image translation) Final Presentation Peter Bromley Generative Models What is generative modeling? Data: Samples from high dimensional probability distribution p real

621 views • 25 slides

Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is

Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is a type of neural net, used in deep learning/machine learning problems The goal of a GAN is to train two simultaneous models: a generative model

441 views • 18 slides

Flow Networks Flow Network: - digraph - weights, called capacities on edges - two

M AXIMUM F LOW How to do it... Why you want it... Where you find it... The Tao of Flow: Let your body go with the flow. -Madonna, Vogue Maximum flow...because youre worth it. -Loreal Go with the flow, Joe.

619 views • 20 slides

Introduction to Generative Models (and GANs) Haoqiang Fan fhq@megvii.com Nov. 2017 Figures

Introduction to Generative Models (and GANs) Haoqiang Fan fhq@megvii.com Nov. 2017 Figures adapted from NIPS 2016 Tutorial Generative Adversarial Networks Generative Models: Learning the Distributions Discriminative: learns the likelihood

1.37k views • 77 slides

Generative recursion Readings: Sections 25, 26, 27, 30, 31 Topics: What is generative recursion?

Generative recursion Readings: Sections 25, 26, 27, 30, 31 Topics: What is generative recursion? Termination Hoares Quicksort Modifying the design recipe Example: breaking strings into lines Intro Termination Quicksort DRecipe Example

319 views • 10 slides

Generative recursion Readings: Sections 25, 26, 27, 30, 31 Topics: What is generative recursion?

554 views • 28 slides

Generative Adversarial Networks Aaron Mishkin UBC MLRG 2018W2 1 Generative Adversial Networks

Generative Adversarial Networks Aaron Mishkin UBC MLRG 2018W2 1 Generative Adversial Networks Two imaginary celebrities that were dreamed up by a random number generator. https://research.nvidia.com/publication/2017-10

665 views • 39 slides

An overview of Boosting Yoav Freund UCSD Plan of talk Generative vs. non-generative

An overview of Boosting Yoav Freund UCSD Plan of talk Generative vs. non-generative modeling Boosting Alternating decision trees Boosting and over-fitting Applications 2 Toy Example Computer receives telephone call

735 views • 61 slides

CS378 - Mobile Computing Audio Android Audio Use the MediaPlayer class Common Audio

CS378 - Mobile Computing Audio Android Audio Use the MediaPlayer class Common Audio Formats supported: MP3, MIDI (.mid and others), Vorbis (.ogg), WAVE (.wav) and others Sources of audio local resources (part of app)

463 views • 29 slides

Sunday Homework 3 : an Diniohlet Allocation Model Latent Generative : Generative model

Dirichet Allocation Latent Lecture ( Part 11 2) : Jordan Yuan Andrea Scribes : , , Midterm This Wednesday : Due Sunday Homework 3 : an Diniohlet Allocation Model Latent Generative : Generative model : Pu Diricwetlw

166 views • 13 slides

Audio Device Client Better and Faster Audio I/O on Web Hongchan Choi Google Chrome Web Audio

Audio Device Client Better and Faster Audio I/O on Web Hongchan Choi Google Chrome Web Audio API Spec Editor (Audio WG) Proposal: Audio Device Client Work-in-progress! (in Audio CG) Proposal: Audio Device Client Low-level audio I/O

454 views • 27 slides

8. Audio databases About digital audio: Advent of digital audio CD in 1983. Order of

8. Audio databases About digital audio: Advent of digital audio CD in 1983. Order of magnitude improvement in overall sound quality and signal-to-noise ratio over the best analog systems. Wide bandwidth required in on-line

486 views • 10 slides

LEARNING GENERATIVE MODELS ACROSS INCOMPARABLE SPACES Cha harlot otte Bunne unne , David

LEARNING GENERATIVE MODELS ACROSS INCOMPARABLE SPACES Cha harlot otte Bunne unne , David Alvarez-Melis, Andreas Krause, Stefanie Jegelka Pos oster #173 173 Poster #173 173 & Charlotte Bunne Generative Modeling generative = network

250 views • 13 slides

CobraNet CobraNet Audio Network Audio Network Overview Overview Developed by Peak Audio

CobraNet CobraNet Audio Network Audio Network Overview Overview Developed by Peak Audio Real-time, high quality, uncompressed digital audio Using standard Ethernet packets and infrastructure => works with any 100 Mbit,

434 views • 7 slides

Cirrus Audio Solutions Cirrus Audio Solutions Home Audio Portable Audio Personal CD Player

Cirrus Audio Solutions Cirrus Audio Solutions Home Audio Portable Audio Personal CD Player A/V Receiver w ith MP3/WMA Flash & HDD based DVD Receiver MP3/WMA Players Home Audio driven by Digital Multi Channel Surround Sound Multi

366 views • 20 slides

Generative Deep Learning Prof. Kuan-Ting Lai 2020/5/12 DeepFake (Intro) Generative Recurrent

Generative Deep Learning Prof. Kuan-Ting Lai 2020/5/12 DeepFake (Intro) Generative Recurrent Networks Douglas Eck (2002), Music Generation using LSTM Alex Graves, Generating Sequences With Recurrent Neural Networks, arXiv (2013),

854 views • 67 slides

GAN-based Photo Video Synthesis Summary of Generative Adversarial Nets Lei Zhang What is

GAN-based Photo Video Synthesis Summary of Generative Adversarial Nets Lei Zhang What is Generative Adversarial Networks (GAN)? Generative - creating new data that depends on the choice of the training set Adversarial - competitive

894 views • 9 slides

Generative Adversarial Networks presented by Ian Goodfellow presentation co-developed with Aaron

Generative Adversarial Networks presented by Ian Goodfellow presentation co-developed with Aaron Courville 1 In todays talk Generative Adversarial Networks Goodfellow et al., NIPS 2014 Conditional Generative

2.84k views • 40 slides

Federal EdTech Legislation and Regulations that You Need to Follow Audio Setup Test Your Audio

Federal EdTech Legislation and Regulations that You Need to Follow Audio Setup Test Your Audio Todays presentation will Click the microphone/gears icon be broadcast using VOIP or only. Go to: Tools > Audio > Audio Setup Wizard This

556 views • 34 slides

Applications of GANs Photo-Realistic Single Image Super-Resolution Using a Generative

Applications of GANs Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks Generative Adversarial Text to Image Synthesis

614 views • 27 slides

Applications of GANs Photo-Realistic Single Image Super-Resolution Using a Generative

666 views • 39 slides