Picture for Mengyue Wu

Mengyue Wu

FakeSound: Deepfake General Audio Detection

Add code
Jun 12, 2024
Viaarxiv icon

Evaluation of data inconsistency for multi-modal sentiment analysis

Jun 05, 2024
Viaarxiv icon

SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound

Add code
Apr 30, 2024
Viaarxiv icon

Towards Reliable and Empathetic Depression-Diagnosis-Oriented Chats

Apr 07, 2024
Viaarxiv icon

A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds

Add code
Mar 07, 2024
Figure 1 for A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds
Figure 2 for A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds
Figure 3 for A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds
Figure 4 for A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds
Viaarxiv icon

Enhancing Audio Generation Diversity with Visual Information

Add code
Mar 02, 2024
Figure 1 for Enhancing Audio Generation Diversity with Visual Information
Figure 2 for Enhancing Audio Generation Diversity with Visual Information
Figure 3 for Enhancing Audio Generation Diversity with Visual Information
Figure 4 for Enhancing Audio Generation Diversity with Visual Information
Viaarxiv icon

A Cognitive Evaluation Benchmark of Image Reasoning and Description for Large Vision Language Models

Add code
Feb 29, 2024
Viaarxiv icon

Phonetic and Lexical Discovery of a Canine Language using HuBERT

Feb 25, 2024
Figure 1 for Phonetic and Lexical Discovery of a Canine Language using HuBERT
Figure 2 for Phonetic and Lexical Discovery of a Canine Language using HuBERT
Figure 3 for Phonetic and Lexical Discovery of a Canine Language using HuBERT
Figure 4 for Phonetic and Lexical Discovery of a Canine Language using HuBERT
Viaarxiv icon

Towards Weakly Supervised Text-to-Audio Grounding

Add code
Jan 05, 2024
Viaarxiv icon

PsyEval: A Comprehensive Large Language Model Evaluation Benchmark for Mental Health

Nov 15, 2023
Viaarxiv icon