Skip to content
Obsidian Vault
Estimator
Initializing search
Home
Past Research
Research Summary
CHAIS
Paper Reviews
Projects
Wiki
Assets
Obsidian Vault
Home
Past Research
Research Summary
CHAIS
CHAIS
Overview
Knowledge
Knowledge
Cocktail Party Problem
Methodology
Methodology
Assisted Listening Technology
Existing Research
Research Plan
Orga
Orga
Reading List
Paper Reviews
Paper Reviews
SFG Mamba
SSMs for Speech Enhancement
Projects
Projects
Ideas
Oscillatory SSM for Speech Enhancement
Oscillatory SSM for Speech Enhancement
Entrained Oscillatory State Space Models for Phase Aware Speech Enhancement
Overview
Project.excalidraw
Results July 26
SSM Domain Evaluation
SSM Evaluation.excalidraw
Selective LinOSS
Selective LinOSS
Model
Selective Oscillatory State-Space Models via Scaled Rotations
Theory
Wiki
Wiki
Overview
Attachments
Attachments
Excalidraw
Excalidraw
Book&Claim
DDDM impl overview
Drawing 2024 04 29 11.03.49.excalidraw
Drawing 2024 04 29 11.29.14.excalidraw
Drawing 2024 05 13 16.49.04.excalidraw
Drawing 2024 05 16 18.34.22.excalidraw
Drawing 2024 05 23 11.23.22.excalidraw
Drawing 2024 05 23 13.06.28.excalidraw
Drawing 2024 05 23 17.46.46.excalidraw
Drawing 2024 05 27 15.34.18.excalidraw
Drawing 2024 05 28 12.05.40.excalidraw
Drawing 2024 05 30 16.29.19.excalidraw
Drawing 2024 06 04 11.12.17.excalidraw
Drawing 2024 06 18 10.33.51.excalidraw
Drawing 2024 06 20 13.37.40.excalidraw
Drawing 2024 06 20 14.43.43.excalidraw
Drawing 2024 07 02 11.03.36.excalidraw
Drawing 2024 07 25 13.15.15.excalidraw
Drawing 2024 09 13 13.27.20.excalidraw
Drawing 2024 09 20 10.34.36.excalidraw
Drawing 2024 09 26 16.36.30.excalidraw
Drawing 2024 09 26 16.44.39.excalidraw
Drawing 2024 09 27 15.15.54.excalidraw
Drawing 2024 09 29 18.15.37.excalidraw
Drawing 2024 09 30 01.22.21.excalidraw
Drawing 2024 11 27 11.26.27.excalidraw
Drawing 2024 12 12 13.37.48.excalidraw
Drawing 2025 01 06 09.22.56.excalidraw
Drawing 2025 01 23 15.54.48.excalidraw
Drawing 2025 03 06 23.23.04.excalidraw
Drawing 2025 03 10 10.21.16.excalidraw
Drawing 2025 04 07 13.20.09.excalidraw
Drawing 2025 04 11 11.21.11.excalidraw
General Concepts
General Concepts
Affective Agent Model
Entanglement of Latent Features
Entropy
Evidence Lower Bound
Generative Modeling
Hamiltonian
Harmonic Oscillator
Integrator
Kullback Leibler divergence
Langevin Dynamics
Manifold Hypothesis
Optimizer
Parallel and Non parallel Training Data
Relative Attribute Rank
Root finding Algorithm
Tractable Distribution
Tweedie's formula
Wasserstein metric
Zero Order Hold
Zero shot Learning
Literature Notes
Literature Notes
Wav2Vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
@balajiEDiffTextImageDiffusionModels2023
Mechanistic Interpretability for AI Safety – A Review
Speech Emotion Recognition Based on Multiple Acoustic Features and Deep Convolutional Neural Network
Cepstral Smoothing of Spectral Filter Gains for Speech Enhancement Without Musical Noise
@changDesignFundamentalsDiffusion2023
Isolating Sources of Disentanglement in Variational Autoencoders
Neural Ordinary Differential Equations
@choiDDDMVCDecoupledDenoising2024
YIN, a fundamental frequency estimator for speech and musica)
Diffusion Models Beat GANs on Image Synthesis
Guided Variational Autoencoder for Disentanglement Learning
@dinhNICENonlinearIndependent2014
Adversarially Learned Inference
Tweedie’s Formula and Selection Bias
Are There Basic Emotions?
Generative adversarial networks
@guoEmoDiffIntensityControllable2023
Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
@higginsVVAELEARNINGBASIC2017
Denoising Diffusion Probabilistic Models
Subspace Diffusion Generative Models
Elucidating the Design Space of Diffusion-Based Generative Models
Disentangling by Factorising
@kimGlowTTSGenerativeFlow2020
Auto-Encoding Variational Bayes
An Introduction to Variational Autoencoders
Diffusion Models already have a Semantic Latent Space
A Brief Introduction to Generative Models
Duration Controllable Voice Conversion via Phoneme-Based Information Bottleneck
Building Naturalistic Emotionally Balanced Speech Corpus by Retrieving Emotional Speech from Existing Podcast Recordings
Decoding of inconsistent communications.
Improved Denoising Diffusion Probabilistic Models
@ohDurFlexEVCDurationFlexibleEmotional2024
Relative attributes
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
@popovGradTTSDiffusionProbabilistic2021
EMOCONV-DIFF: Diffusion-based Speech Emotion Conversion for Non-parallel and In-the-wild Data
In-the-wild Speech Emotion Conversion Using Disentangled Self-Supervised Representations and Neural Vocoder-based Resynthesis
@renFastSpeechFastRobust2019
A circumplex model of affect.
@schullerComputationalParalinguisticsEmotion2013
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Generative Modeling by Estimating Gradients of the Data Distribution
Improved Techniques for Training Score-Based Generative Models
Score-Based Generative Modeling through Stochastic Differential Equations
An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era
Score-based Generative Modeling in Latent Space
@wagnerDawnTransformerEra2023
Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
Non-Parallel Sequence-to-Sequence Voice Conversion With Disentangled Linguistic and Speaker Representations
@zhouEmotionalVoiceConversion2022
@zhuS3VAESelfSupervisedSequential2020
Models
Models
EnCodec
G2P
Wav2Vec 2.0
Emotion Conversion
Emotion Conversion
EmoConv Diff
Emotional Voice Conversion (EVC)
In the wild SEC
General Models
General Models
Autoregressive Models
Normalizing Flows
Spiking Neural Networks
Seq2seq model
Autoencoder
Autoencoder
ALI VAE
Autoencoder (AE)
Factor VAE
S3VAE
Supervised Guided VAE
U Net
Unsupervised Guided VAE
Variational Autoencoder
beta TCVAE
beta VAE
Diffusion Models
Diffusion Models
ComputerScience #AI
Disentanglement in Diffusion Models
Latent Score Based Generative Model
Score Based Diffusion Model
Generative Adversarial Networks
Generative Adversarial Networks
ComputerScience #AI
Unrolled GAN
Speech Enhancement
Speech Enhancement
MP SENet
SEMamba
USEMamba
Speech Synthesis
Speech Synthesis
DiffVC
DiffVoice
E3 TTS
EmoDiff
EmoMix
ComputerScience #Speech #Emotion
Grad TTS
HiFiGAN
MixedEmotions
NANSY
DDDM VC
DDDM VC
Architecture
Code Base
Disentangled Denoising
Overview
Potential Extensions
State Space Models
State Space Models
HiPPO
LRU
LinOSS
Mamba
S4
State Space Model
State Space Models
Psychology
Psychology
Emotion
Emotion
Ekman's Big Six
Emotion
Russell's Circumplex Model
Neuroscience
Neuroscience
Global Neuronal Workspace (GNW)
Neural Oscillation
Neural Spiking
Phase Locking
Predictive Coding
Speech Processing (Basics)
Speech Processing (Basics)
Analysis Window
Autoregressive Moving Average (ARMA)
Cepstrum
Complex Integral
Differential Equation
Discrete Cosine Transformation
Estimator
Estimator
Table of contents
Minimum Mean Square Error (MMSE)
Maximum Likelihood Estimation (MLE)
Formant
Fourier Transformation
Fundamental Frequency (F0)
LTI System
Mel frequency Cepstrum Coefficients (MFCC)
Phonetic Transcription
Power Spectral Density (PSD)
Quantization
Source Filter Model
Spectral Envelope
Spectral Leakage
Spectral Transformation
Speech Coding
Speech Enhancement Evaluation Metrics
Speech Enhancement
Speech Recognition
Speech Signal Processing Overview
Transfer Function
Vocoding
Wiener Filter
Speech Synthesis
Speech Synthesis
Affective Speech Synthesis (ASS)
Datasets for Emotional Speech
Duration Prediction
Speaker Recognition
Speech Emotion Recognition (SER)
Text to Speech Synthesis (TTS)
Voice Conversion (VC)
Yingram
Assets
Assets
Excalidraw
Excalidraw
Drawing 2025 10 10 13.56.23.excalidraw
Drawing 2025 10 10 14.15.58.excalidraw
Drawing 2025 12 01 14.34.44.excalidraw
Drawing 2026 06 25 15.15.59.excalidraw
Drawing 2026 07 30 09.45.44.excalidraw
Table of contents
Minimum Mean Square Error (MMSE)
Maximum Likelihood Estimation (MLE)
Estimator
Minimum Mean Square Error (MMSE)
¶
…
Maximum Likelihood Estimation (MLE)
¶
…