Alert button

"Information": models, code, and papers
Alert button

A Sidecar Separator Can Convert a Single-Speaker Speech Recognition System to a Multi-Speaker One

Feb 20, 2023
Lingwei Meng, Jiawen Kang, Mingyu Cui, Yuejiao Wang, Xixin Wu, Helen Meng

Figure 1 for A Sidecar Separator Can Convert a Single-Speaker Speech Recognition System to a Multi-Speaker One
Figure 2 for A Sidecar Separator Can Convert a Single-Speaker Speech Recognition System to a Multi-Speaker One
Figure 3 for A Sidecar Separator Can Convert a Single-Speaker Speech Recognition System to a Multi-Speaker One
Figure 4 for A Sidecar Separator Can Convert a Single-Speaker Speech Recognition System to a Multi-Speaker One
Viaarxiv icon

Query-Utterance Attention with Joint modeling for Query-Focused Meeting Summarization

Mar 08, 2023
Xingxian Liu, Bin Duan, Bo Xiao, Yajing Xu

Figure 1 for Query-Utterance Attention with Joint modeling for Query-Focused Meeting Summarization
Figure 2 for Query-Utterance Attention with Joint modeling for Query-Focused Meeting Summarization
Figure 3 for Query-Utterance Attention with Joint modeling for Query-Focused Meeting Summarization
Figure 4 for Query-Utterance Attention with Joint modeling for Query-Focused Meeting Summarization
Viaarxiv icon

Can Membership Inferencing be Refuted?

Mar 08, 2023
Zhifeng Kong, Amrita Roy Chowdhury, Kamalika Chaudhuri

Figure 1 for Can Membership Inferencing be Refuted?
Figure 2 for Can Membership Inferencing be Refuted?
Figure 3 for Can Membership Inferencing be Refuted?
Figure 4 for Can Membership Inferencing be Refuted?
Viaarxiv icon

DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model

Feb 26, 2023
Yichen Peng, Chunqi Zhao, Haoran Xie, Tsukasa Fukusato, Kazunori Miyata

Figure 1 for DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model
Figure 2 for DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model
Figure 3 for DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model
Figure 4 for DiffFaceSketch: High-Fidelity Face Image Synthesis with Sketch-Guided Latent Diffusion Model
Viaarxiv icon

Meme Sentiment Analysis Enhanced with Multimodal Spatial Encoding and Facial Embedding

Mar 03, 2023
Muzhaffar Hazman, Susan McKeever, Josephine Griffith

Viaarxiv icon

CONTAIN: A Community-based Algorithm for Network Immunization

Mar 03, 2023
Özgur Coban, Ciprian-Octavian Truică, Elena-Simona Apostol

Figure 1 for CONTAIN: A Community-based Algorithm for Network Immunization
Figure 2 for CONTAIN: A Community-based Algorithm for Network Immunization
Figure 3 for CONTAIN: A Community-based Algorithm for Network Immunization
Figure 4 for CONTAIN: A Community-based Algorithm for Network Immunization
Viaarxiv icon

Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms

Mar 07, 2023
Ankit Shah, Shuyi Chen, Kejun Zhou, Yue Chen, Bhiksha Raj

Figure 1 for Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms
Figure 2 for Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms
Figure 3 for Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms
Figure 4 for Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms
Viaarxiv icon

A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments

Mar 07, 2023
Zhaoxi Mu, Xinyu Yang, Xiangyuan Yang, Wenjing Zhu

Figure 1 for A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments
Figure 2 for A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments
Figure 3 for A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments
Figure 4 for A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments
Viaarxiv icon

Extracting Victim Counts from Text

Feb 23, 2023
Mian Zhong, Shehzaad Dhuliawala, Niklas Stoehr

Figure 1 for Extracting Victim Counts from Text
Figure 2 for Extracting Victim Counts from Text
Figure 3 for Extracting Victim Counts from Text
Figure 4 for Extracting Victim Counts from Text
Viaarxiv icon

XL-MIMO Channel Modeling and Prediction for Wireless Power Transfer

Feb 23, 2023
Benjamin J. B. Deutschmann, Thomas Wilding, Maximilian Graber, Klaus Witrisal

Figure 1 for XL-MIMO Channel Modeling and Prediction for Wireless Power Transfer
Figure 2 for XL-MIMO Channel Modeling and Prediction for Wireless Power Transfer
Figure 3 for XL-MIMO Channel Modeling and Prediction for Wireless Power Transfer
Figure 4 for XL-MIMO Channel Modeling and Prediction for Wireless Power Transfer
Viaarxiv icon