Picture for Vishwanath Pratap Singh

Vishwanath Pratap Singh

ROAR: Reinforcing Original to Augmented Data Ratio Dynamics for Wav2Vec2.0 Based ASR

Jun 14, 2024
Viaarxiv icon

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

Add code
Feb 23, 2024
Viaarxiv icon

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

Jun 13, 2023
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

Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech

Mar 13, 2022
Figure 1 for Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech
Figure 2 for Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech
Figure 3 for Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech
Figure 4 for Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech
Viaarxiv icon

A Mixture of Expert Based Deep Neural Network for Improved ASR

Dec 02, 2021
Figure 1 for A Mixture of Expert Based Deep Neural Network for Improved ASR
Figure 2 for A Mixture of Expert Based Deep Neural Network for Improved ASR
Figure 3 for A Mixture of Expert Based Deep Neural Network for Improved ASR
Figure 4 for A Mixture of Expert Based Deep Neural Network for Improved ASR
Viaarxiv icon

A higher order Minkowski loss for improved prediction ability of acoustic model in ASR

Dec 02, 2021
Figure 1 for A higher order Minkowski loss for improved prediction ability of acoustic model in ASR
Figure 2 for A higher order Minkowski loss for improved prediction ability of acoustic model in ASR
Figure 3 for A higher order Minkowski loss for improved prediction ability of acoustic model in ASR
Figure 4 for A higher order Minkowski loss for improved prediction ability of acoustic model in ASR
Viaarxiv icon

SRIB Submission to Interspeech 2021 DiCOVA Challenge

Jun 15, 2021
Figure 1 for SRIB Submission to Interspeech 2021 DiCOVA Challenge
Figure 2 for SRIB Submission to Interspeech 2021 DiCOVA Challenge
Figure 3 for SRIB Submission to Interspeech 2021 DiCOVA Challenge
Figure 4 for SRIB Submission to Interspeech 2021 DiCOVA Challenge
Viaarxiv icon