Speak in the Scene: Diffusion-based Acoustic Scene Transfer toward Immersive Speech Generation
Posts by Category
- Conference 21
- Audiovisual 7
- Journal 3
- Speech separation 3
- Source localization 2
- Multimodal Learning 2
- Speaker representation 2
- Speech disentanglement 2
- Speech enhancement 2
- Speech restoration 2
- Microphoone array 1
- Multi-channel 1
- Active learning 1
- Speech recognition 1
- Cross-modal retrieval 1
- Speaker recognition 1
- Synchronisation 1
- Separation 1
- Active speaker detection 1
- Phase reconstruction 1
- Anti-spoofing 1
- Speaker Verification 1
- SASV Challenge 1
- Crossmodal 1
- Keyword spotting 1
- Diffusion 1
- Self-supervised learning 1
- Multi-lingual 1
- Mixture-of-experts 1
- Audio-visual 1
- Speech synthesis 1
- Pitch estimation 1
- Periodicity 1
- Speech generation 1
- Acoustic scene transfer 1
Conference
HD-DEMUCS: General Speech Restoration with Heterogeneous Decoders
MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion
Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech
MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition
An Empirical Study on Speech Restoration Guided by Self-supervised Speech Representation
Diffusion-based Generative Speech Source Separation
Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting
SASV 2022: The First Spoofing-Aware Speaker Verification Challenge
Baseline Systems for the First Spoofing-Aware Speaker Verification Challenge: Score and Embedding Fusion
Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement
Look Who’s Talking: Active Speaker Detection in the Wild
Looking Into Your Speech: Learning Cross-Modal Affinity for Audio-Visual Speech Separation
End-To-End Lip Synchronisation Based on Pattern Classification
Intra-Class Variation Reduction of Speaker Representation in Disentanglement Framework
FaceFilter: Audio-Visual Speech Separation using Still Images
Seeing Voices and Hearing Voices: Learning Discriminative Embeddings Using Cross-Modal Self-Supervision
Gradient-based Active Learning Query Strategy for End-to-end Speech Recognition
Perfect Match: Improved Cross-modal Embeddings for Audio-visual Synchronisation
A Study on Search Grid Points for Data-Driven 3-D Beamsteering
Audiovisual
Look Who’s Talking: Active Speaker Detection in the Wild
Looking Into Your Speech: Learning Cross-Modal Affinity for Audio-Visual Speech Separation
End-To-End Lip Synchronisation Based on Pattern Classification
FaceFilter: Audio-Visual Speech Separation using Still Images
Seeing Voices and Hearing Voices: Learning Discriminative Embeddings Using Cross-Modal Self-Supervision
Perfect Match: Self-Supervised Embeddings for Cross-Modal Retrieval
Perfect Match: Improved Cross-modal Embeddings for Audio-visual Synchronisation
Journal
A Study on Speech Disentanglement Framework based on Adversarial Learning for Speaker Recognition
Perfect Match: Self-Supervised Embeddings for Cross-Modal Retrieval
Generic Uniform Search Grid Generation Algorithm for Far-field Source Localization
Speech separation
Diffusion-based Generative Speech Source Separation
FaceFilter: Audio-Visual Speech Separation using Still Images
Source localization
Generic Uniform Search Grid Generation Algorithm for Far-field Source Localization
A Study on Search Grid Points for Data-Driven 3-D Beamsteering
Multimodal Learning
Perfect Match: Self-Supervised Embeddings for Cross-Modal Retrieval
Perfect Match: Improved Cross-modal Embeddings for Audio-visual Synchronisation
Speaker representation
Speech disentanglement
A Study on Speech Disentanglement Framework based on Adversarial Learning for Speaker Recognition
Speech enhancement
HD-DEMUCS: General Speech Restoration with Heterogeneous Decoders
Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement
Speech restoration
HD-DEMUCS: General Speech Restoration with Heterogeneous Decoders
An Empirical Study on Speech Restoration Guided by Self-supervised Speech Representation
Microphoone array
A Study on Search Grid Points for Data-Driven 3-D Beamsteering
Multi-channel
Generic Uniform Search Grid Generation Algorithm for Far-field Source Localization
Active learning
Gradient-based Active Learning Query Strategy for End-to-end Speech Recognition
Speech recognition
Gradient-based Active Learning Query Strategy for End-to-end Speech Recognition
Cross-modal retrieval
Speaker recognition
A Study on Speech Disentanglement Framework based on Adversarial Learning for Speaker Recognition
Synchronisation
End-To-End Lip Synchronisation Based on Pattern Classification
Separation
Looking Into Your Speech: Learning Cross-Modal Affinity for Audio-Visual Speech Separation
Active speaker detection
Look Who’s Talking: Active Speaker Detection in the Wild
Phase reconstruction
Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement
Anti-spoofing
Speaker Verification
SASV Challenge
SASV 2022: The First Spoofing-Aware Speaker Verification Challenge
Crossmodal
Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting
Keyword spotting
Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting
Diffusion
Diffusion-based Generative Speech Source Separation
Self-supervised learning
An Empirical Study on Speech Restoration Guided by Self-supervised Speech Representation
Multi-lingual
MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition
Mixture-of-experts
MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition
Audio-visual
Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech
Speech synthesis
Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech