Picture for Yiwei Ding

Yiwei Ding

Understanding Pedestrian Movement Using Urban Sensing Technologies: The Promise of Audio-based Sensors

Add code
Jun 14, 2024
Viaarxiv icon

Embedding Compression for Teacher-to-Student Knowledge Transfer

Feb 09, 2024
Viaarxiv icon

A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation

Add code
Sep 07, 2023
Figure 1 for A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation
Figure 2 for A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation
Figure 3 for A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation
Figure 4 for A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation
Viaarxiv icon

Audio Embeddings as Teachers for Music Classification

Add code
Jun 30, 2023
Figure 1 for Audio Embeddings as Teachers for Music Classification
Figure 2 for Audio Embeddings as Teachers for Music Classification
Figure 3 for Audio Embeddings as Teachers for Music Classification
Figure 4 for Audio Embeddings as Teachers for Music Classification
Viaarxiv icon

MusicFace: Music-driven Expressive Singing Face Synthesis

Mar 24, 2023
Figure 1 for MusicFace: Music-driven Expressive Singing Face Synthesis
Figure 2 for MusicFace: Music-driven Expressive Singing Face Synthesis
Figure 3 for MusicFace: Music-driven Expressive Singing Face Synthesis
Figure 4 for MusicFace: Music-driven Expressive Singing Face Synthesis
Viaarxiv icon

The DKU-Tencent System for the VoxCeleb Speaker Recognition Challenge 2022

Add code
Oct 11, 2022
Figure 1 for The DKU-Tencent System for the VoxCeleb Speaker Recognition Challenge 2022
Figure 2 for The DKU-Tencent System for the VoxCeleb Speaker Recognition Challenge 2022
Figure 3 for The DKU-Tencent System for the VoxCeleb Speaker Recognition Challenge 2022
Figure 4 for The DKU-Tencent System for the VoxCeleb Speaker Recognition Challenge 2022
Viaarxiv icon

I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation

Jun 27, 2022
Figure 1 for I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation
Figure 2 for I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation
Figure 3 for I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation
Figure 4 for I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation
Viaarxiv icon

Rep Works in Speaker Verification

Oct 19, 2021
Figure 1 for Rep Works in Speaker Verification
Figure 2 for Rep Works in Speaker Verification
Figure 3 for Rep Works in Speaker Verification
Figure 4 for Rep Works in Speaker Verification
Viaarxiv icon

Multi-query multi-head attention pooling and Inter-topK penalty for speaker verification

Oct 12, 2021
Figure 1 for Multi-query multi-head attention pooling and Inter-topK penalty for speaker verification
Figure 2 for Multi-query multi-head attention pooling and Inter-topK penalty for speaker verification
Figure 3 for Multi-query multi-head attention pooling and Inter-topK penalty for speaker verification
Figure 4 for Multi-query multi-head attention pooling and Inter-topK penalty for speaker verification
Viaarxiv icon

Poformer: A simple pooling transformer for speaker verification

Oct 10, 2021
Figure 1 for Poformer: A simple pooling transformer for speaker verification
Figure 2 for Poformer: A simple pooling transformer for speaker verification
Figure 3 for Poformer: A simple pooling transformer for speaker verification
Figure 4 for Poformer: A simple pooling transformer for speaker verification
Viaarxiv icon