Image de couverture de livre

Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bovbjerg, Holger Severin, Østergaard, Jan, Jensen, Jesper, Tan, Zheng-Hua
Format:	Preprint
Publié:	2025
Sujets:	Audio and Speech Processing Machine Learning Sound 68T10 I.2.6
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Self-supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions
par: Bovbjerg, Holger Severin, et autres
Publié: (2023)

Learning Robust Spatial Representations from Binaural Audio through Feature Distillation
par: Bovbjerg, Holger Severin, et autres
Publié: (2025)

Noise-Robust Keyword Spotting through Self-supervised Pretraining
par: Mørk, Jacob, et autres
Publié: (2024)

Rethinking Masking Strategies for Masked Prediction-based Audio Self-supervised Learning
par: Niizumi, Daisuke, et autres
Publié: (2026)

Joint Feature and Output Distillation for Low-complexity Acoustic Scene Classification
par: Li, Haowen, et autres
Publié: (2025)

Audio-based Kinship Verification Using Age Domain Conversion
par: Sun, Qiyang, et autres
Publié: (2024)

Deep low-latency joint speech transmission and enhancement over a gaussian channel
par: Bokaei, Mohammad, et autres
Publié: (2024)

MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
par: Kühne, Nikolai Lund, et autres
Publié: (2025)

Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech Enhancement
par: Kühne, Nikolai Lund, et autres
Publié: (2025)

xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
par: Kühne, Nikolai Lund, et autres
Publié: (2025)

Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization
par: Thienpondt, Jenthe, et autres
Publié: (2024)

Make Some Noise: Towards LLM audio reasoning and generation using sound tokens
par: Mehta, Shivam, et autres
Publié: (2025)

A Unified Model For Voice and Accent Conversion In Speech and Singing using Self-Supervised Learning and Feature Extraction
par: Cheripally, Sowmya
Publié: (2024)

ChordSync: Conformer-Based Alignment of Chord Annotations to Music Audio
par: Poltronieri, Andrea, et autres
Publié: (2024)

Symbolic Audio Classification via Modal Decision Tree Learning
par: Marzano, Enrico, et autres
Publié: (2025)

Joint Minimum Processing Beamforming and Near-end Listening Enhancement
par: Fuglsig, Andreas J., et autres
Publié: (2023)

Profile-Error-Tolerant Target-Speaker Voice Activity Detection
par: Wang, Dongmei, et autres
Publié: (2023)

Universal Speaker Embedding Free Target Speaker Extraction and Personal Voice Activity Detection
par: Zeng, Bang, et autres
Publié: (2025)

Experimental Study: Enhancing Voice Spoofing Detection Models with wav2vec 2.0
par: Kang, Taein, et autres
Publié: (2024)

Monaural Multi-Speaker Speech Separation Using Efficient Transformer Model
par: Rijal, S., et autres
Publié: (2023)

STAR: Speech-to-Audio Generation via Representation Learning
par: Xie, Zeyu, et autres
Publié: (2025)

FakeSound2: A Benchmark for Explainable and Generalizable Deepfake Sound Detection
par: Xie, Zeyu, et autres
Publié: (2025)

PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation
par: Xie, Zeyu, et autres
Publié: (2024)

AudioTime: A Temporally-aligned Audio-text Benchmark Dataset
par: Xie, Zeyu, et autres
Publié: (2024)

CAST-TTS: A Simple Cross-Attention Framework for Unified Timbre Control in TTS
par: Zheng, Zihao, et autres
Publié: (2026)

PicoAudio2: Temporal Controllable Text-to-Audio Generation with Natural Language Description
par: Zheng, Zihao, et autres
Publié: (2025)

FakeSound: Deepfake General Audio Detection
par: Xie, Zeyu, et autres
Publié: (2024)

Passive Underwater Acoustic Signal Separation based on Feature Decoupling Dual-path Network
par: Liu, Yucheng, et autres
Publié: (2025)

Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching
par: Chen, Zhengyang, et autres
Publié: (2024)

DINO-VITS: Data-Efficient Zero-Shot TTS with Self-Supervised Speaker Verification Loss for Noise Robustness
par: Pankov, Vikentii, et autres
Publié: (2023)

Investigating the Design Space of Diffusion Models for Speech Enhancement
par: Gonzalez, Philippe, et autres
Publié: (2023)

Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler
par: Gonzalez, Philippe, et autres
Publié: (2023)

Local Diagnostics of Continuous Normalizing Flow for Out-of-Distribution Detection
par: Cao, Xinwei, et autres
Publié: (2026)

SemAlignVC: Enhancing zero-shot timbre conversion using semantic alignment
par: Mehta, Shivam, et autres
Publié: (2025)

TuneGenie: Reasoning-based LLM agents for preferential music generation
par: Pandey, Amitesh, et autres
Publié: (2025)

KinSPEAK: Improving speech recognition for Kinyarwanda via semi-supervised learning methods
par: Nzeyimana, Antoine
Publié: (2023)

Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models
par: Phukan, Orchid Chetia, et autres
Publié: (2024)

Window Size Versus Accuracy Experiments in Voice Activity Detectors
par: McKinnon, Max, et autres
Publié: (2026)

Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution
par: Phukan, Orchid Chetia, et autres
Publié: (2024)

Strong Alone, Stronger Together: Synergizing Modality-Binding Foundation Models with Optimal Transport for Non-Verbal Emotion Recognition
par: Phukan, Orchid Chetia, et autres
Publié: (2024)