Picture for Haibin Wu

Haibin Wu

CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems

Add code
Jun 11, 2024
Viaarxiv icon

Neural Codec-based Adversarial Sample Detection for Speaker Verification

Jun 07, 2024
Viaarxiv icon

Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition

Jun 07, 2024
Viaarxiv icon

Singing Voice Graph Modeling for SingFake Detection

Add code
Jun 05, 2024
Viaarxiv icon

A Large-Scale Evaluation of Speech Foundation Models

Add code
Apr 15, 2024
Viaarxiv icon

EMO-SUPERB: An In-depth Look at Speech Emotion Recognition

Add code
Feb 22, 2024
Viaarxiv icon

Codec-SUPERB: An In-Depth Analysis of Sound Codec Models

Add code
Feb 20, 2024
Viaarxiv icon

Towards audio language modeling -- an overview

Feb 20, 2024
Figure 1 for Towards audio language modeling -- an overview
Figure 2 for Towards audio language modeling -- an overview
Figure 3 for Towards audio language modeling -- an overview
Figure 4 for Towards audio language modeling -- an overview
Viaarxiv icon

Scalable Ensemble-based Detection Method against Adversarial Attacks for speaker verification

Dec 14, 2023
Viaarxiv icon

AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models

Add code
Sep 19, 2023
Figure 1 for AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models
Figure 2 for AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models
Figure 3 for AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models
Viaarxiv icon