Picture for Quanxiu Wang

Quanxiu Wang

Prior-agnostic Multi-scale Contrastive Text-Audio Pre-training for Parallelized TTS Frontend Modeling

Add code
Apr 14, 2024
Viaarxiv icon

Knowledge-aware Collaborative Filtering with Pre-trained Language Model for Personalized Review-based Rating Prediction

Add code
Aug 02, 2023
Viaarxiv icon

TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection

Add code
Jun 27, 2023
Figure 1 for TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection
Figure 2 for TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection
Figure 3 for TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection
Viaarxiv icon

Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder

Add code
Jul 01, 2021
Figure 1 for Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder
Figure 2 for Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder
Figure 3 for Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder
Figure 4 for Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder
Viaarxiv icon