Picture for Dejun Zhang

Dejun Zhang

An Intra-BRNN and GB-RVQ Based END-TO-END Neural Audio Codec

Add code
Feb 02, 2024
Viaarxiv icon

Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model

Add code
Apr 07, 2022
Figure 1 for Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model
Figure 2 for Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model
Figure 3 for Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model
Figure 4 for Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model
Viaarxiv icon

PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information

Add code
Mar 31, 2021
Figure 1 for PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information
Figure 2 for PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information
Figure 3 for PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information
Figure 4 for PointShuffleNet: Learning Non-Euclidean Features with Homotopy Equivalence and Mutual Information
Viaarxiv icon