Alert button
Picture for Md Sahidullah

Md Sahidullah

Alert button

Exploring Green AI for Audio Deepfake Detection

Mar 21, 2024
Subhajit Saha, Md Sahidullah, Swagatam Das

Viaarxiv icon

Assessing the Robustness of Spectral Clustering for Deep Speaker Diarization

Mar 21, 2024
Nikhil Raghav, Md Sahidullah

Viaarxiv icon

ChildAugment: Data Augmentation Methods for Zero-Resource Children's Speaker Verification

Feb 23, 2024
Vishwanath Pratap Singh, Md Sahidullah, Tomi Kinnunen

Viaarxiv icon

Generalizing Speaker Verification for Spoof Awareness in the Embedding Space

Jan 28, 2024
Xuechen Liu, Md Sahidullah, Kong Aik Lee, Tomi Kinnunen

Viaarxiv icon

Speaker Verification Across Ages: Investigating Deep Speaker Embedding Sensitivity to Age Mismatch in Enrollment and Test Speech

Jun 13, 2023
Vishwanath Pratap Singh, Md Sahidullah, Tomi Kinnunen

Figure 1 for Speaker Verification Across Ages: Investigating Deep Speaker Embedding Sensitivity to Age Mismatch in Enrollment and Test Speech
Figure 2 for Speaker Verification Across Ages: Investigating Deep Speaker Embedding Sensitivity to Age Mismatch in Enrollment and Test Speech
Figure 3 for Speaker Verification Across Ages: Investigating Deep Speaker Embedding Sensitivity to Age Mismatch in Enrollment and Test Speech
Figure 4 for Speaker Verification Across Ages: Investigating Deep Speaker Embedding Sensitivity to Age Mismatch in Enrollment and Test Speech
Viaarxiv icon

Stuttering Detection Using Speaker Representations and Self-supervised Contextual Embeddings

Jun 01, 2023
Shakeel A. Sheikh, Md Sahidullah, Fabrice Hirsch, Slim Ouni

Figure 1 for Stuttering Detection Using Speaker Representations and Self-supervised Contextual Embeddings
Figure 2 for Stuttering Detection Using Speaker Representations and Self-supervised Contextual Embeddings
Figure 3 for Stuttering Detection Using Speaker Representations and Self-supervised Contextual Embeddings
Figure 4 for Stuttering Detection Using Speaker Representations and Self-supervised Contextual Embeddings
Viaarxiv icon

Towards single integrated spoofing-aware speaker verification embeddings

Jun 01, 2023
Sung Hwan Mun, Hye-jin Shim, Hemlata Tak, Xin Wang, Xuechen Liu, Md Sahidullah, Myeonghun Jeong, Min Hyun Han, Massimiliano Todisco, Kong Aik Lee, Junichi Yamagishi, Nicholas Evans, Tomi Kinnunen, Nam Soo Kim, Jee-weon Jung

Figure 1 for Towards single integrated spoofing-aware speaker verification embeddings
Figure 2 for Towards single integrated spoofing-aware speaker verification embeddings
Figure 3 for Towards single integrated spoofing-aware speaker verification embeddings
Figure 4 for Towards single integrated spoofing-aware speaker verification embeddings
Viaarxiv icon

How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning

May 31, 2023
Hye-jin Shim, Rosa González Hautamäki, Md Sahidullah, Tomi Kinnunen

Figure 1 for How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning
Figure 2 for How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning
Figure 3 for How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning
Figure 4 for How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning
Viaarxiv icon

Speaker-Aware Anti-Spoofing

Mar 02, 2023
Xuechen Liu, Md Sahidullah, Kong Aik Lee, Tomi Kinnunen

Figure 1 for Speaker-Aware Anti-Spoofing
Figure 2 for Speaker-Aware Anti-Spoofing
Figure 3 for Speaker-Aware Anti-Spoofing
Figure 4 for Speaker-Aware Anti-Spoofing
Viaarxiv icon

Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification

Mar 02, 2023
Xuechen Liu, Md Sahidullah, Tomi Kinnunen

Figure 1 for Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification
Figure 2 for Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification
Figure 3 for Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification
Figure 4 for Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification
Viaarxiv icon