Alert button
Picture for John H. L. Hansen

John H. L. Hansen

Alert button

Single-channel speech separation using Soft-minimum Permutation Invariant Training

Nov 16, 2021
Midia Yousefi, John H. L. Hansen

Figure 1 for Single-channel speech separation using Soft-minimum Permutation Invariant Training
Figure 2 for Single-channel speech separation using Soft-minimum Permutation Invariant Training
Figure 3 for Single-channel speech separation using Soft-minimum Permutation Invariant Training
Figure 4 for Single-channel speech separation using Soft-minimum Permutation Invariant Training
Viaarxiv icon

Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network

Oct 30, 2021
Midia Yousefi, John H. L. Hansen

Figure 1 for Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network
Figure 2 for Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network
Figure 3 for Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network
Figure 4 for Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network
Viaarxiv icon

Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora

Sep 23, 2021
Szu-Jui Chen, Wei Xia, John H. L. Hansen

Figure 1 for Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora
Figure 2 for Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora
Figure 3 for Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora
Figure 4 for Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora
Viaarxiv icon

DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning

Dec 12, 2020
Mufan Sang, Wei Xia, John H. L. Hansen

Figure 1 for DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning
Figure 2 for DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning
Figure 3 for DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning
Viaarxiv icon

Respiratory Distress Detection from Telephone Speech using Acoustic and Prosodic Features

Nov 15, 2020
Meemnur Rashid, Kaisar Ahmed Alman, Khaled Hasan, John H. L. Hansen, Taufiq Hasan

Figure 1 for Respiratory Distress Detection from Telephone Speech using Acoustic and Prosodic Features
Figure 2 for Respiratory Distress Detection from Telephone Speech using Acoustic and Prosodic Features
Figure 3 for Respiratory Distress Detection from Telephone Speech using Acoustic and Prosodic Features
Figure 4 for Respiratory Distress Detection from Telephone Speech using Acoustic and Prosodic Features
Viaarxiv icon

Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias

Sep 21, 2020
Mufan Sang, Wei Xia, John H. L. Hansen

Figure 1 for Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias
Figure 2 for Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias
Figure 3 for Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias
Viaarxiv icon

Speaker Representation Learning using Global Context Guided Channel and Time-Frequency Transformations

Sep 09, 2020
Wei Xia, John H. L. Hansen

Figure 1 for Speaker Representation Learning using Global Context Guided Channel and Time-Frequency Transformations
Figure 2 for Speaker Representation Learning using Global Context Guided Channel and Time-Frequency Transformations
Figure 3 for Speaker Representation Learning using Global Context Guided Channel and Time-Frequency Transformations
Figure 4 for Speaker Representation Learning using Global Context Guided Channel and Time-Frequency Transformations
Viaarxiv icon

Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification

Sep 09, 2020
Zhenyu Wang, Wei Xia, John H. L. Hansen

Figure 1 for Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification
Figure 2 for Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification
Figure 3 for Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification
Figure 4 for Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification
Viaarxiv icon

Sensor Fusion of Camera and Cloud Digital Twin Information for Intelligent Vehicles

Jul 08, 2020
Yongkang Liu, Ziran Wang, Kyungtae Han, Zhenyu Shou, Prashant Tiwari, John H. L. Hansen

Figure 1 for Sensor Fusion of Camera and Cloud Digital Twin Information for Intelligent Vehicles
Figure 2 for Sensor Fusion of Camera and Cloud Digital Twin Information for Intelligent Vehicles
Figure 3 for Sensor Fusion of Camera and Cloud Digital Twin Information for Intelligent Vehicles
Figure 4 for Sensor Fusion of Camera and Cloud Digital Twin Information for Intelligent Vehicles
Viaarxiv icon