Picture for Lu Fan

Lu Fan

Do self-supervised speech and language models extract similar representations as human brain?

Oct 07, 2023
Viaarxiv icon

Neural2Speech: A Transfer Learning Framework for Neural-Driven Speech Reconstruction

Add code
Oct 07, 2023
Viaarxiv icon

Leveraging Label Information for Multimodal Emotion Recognition

Add code
Sep 05, 2023
Figure 1 for Leveraging Label Information for Multimodal Emotion Recognition
Figure 2 for Leveraging Label Information for Multimodal Emotion Recognition
Figure 3 for Leveraging Label Information for Multimodal Emotion Recognition
Figure 4 for Leveraging Label Information for Multimodal Emotion Recognition
Viaarxiv icon

Co-evolving Vector Quantization for ID-based Recommendation

Add code
Sep 02, 2023
Viaarxiv icon

Neighborhood-based Hard Negative Mining for Sequential Recommendation

Add code
Jun 12, 2023
Figure 1 for Neighborhood-based Hard Negative Mining for Sequential Recommendation
Figure 2 for Neighborhood-based Hard Negative Mining for Sequential Recommendation
Figure 3 for Neighborhood-based Hard Negative Mining for Sequential Recommendation
Figure 4 for Neighborhood-based Hard Negative Mining for Sequential Recommendation
Viaarxiv icon

Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark

Add code
Jun 10, 2023
Figure 1 for Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark
Figure 2 for Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark
Figure 3 for Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark
Figure 4 for Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark
Viaarxiv icon

OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition

Jun 05, 2023
Figure 1 for OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition
Figure 2 for OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition
Figure 3 for OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition
Figure 4 for OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition
Viaarxiv icon

UFO2: A unified pre-training framework for online and offline speech recognition

Oct 26, 2022
Figure 1 for UFO2: A unified pre-training framework for online and offline speech recognition
Figure 2 for UFO2: A unified pre-training framework for online and offline speech recognition
Figure 3 for UFO2: A unified pre-training framework for online and offline speech recognition
Figure 4 for UFO2: A unified pre-training framework for online and offline speech recognition
Viaarxiv icon

Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training

Add code
Jun 17, 2021
Figure 1 for Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training
Figure 2 for Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training
Figure 3 for Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training
Figure 4 for Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training
Viaarxiv icon