Picture for Wang Geng

Wang Geng

Disentangling Age and Identity with a Mutual Information Minimization Approach for Cross-Age Speaker Verification

Add code
Sep 24, 2024
Figure 1 for Disentangling Age and Identity with a Mutual Information Minimization Approach for Cross-Age Speaker Verification
Figure 2 for Disentangling Age and Identity with a Mutual Information Minimization Approach for Cross-Age Speaker Verification
Figure 3 for Disentangling Age and Identity with a Mutual Information Minimization Approach for Cross-Age Speaker Verification
Figure 4 for Disentangling Age and Identity with a Mutual Information Minimization Approach for Cross-Age Speaker Verification
Viaarxiv icon

Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM

Add code
Sep 24, 2024
Figure 1 for Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM
Figure 2 for Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM
Figure 3 for Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM
Figure 4 for Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM
Viaarxiv icon

VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing

Add code
Aug 11, 2024
Viaarxiv icon

Dynamic Multi-scale Convolution for Dialect Identification

Add code
Aug 02, 2021
Figure 1 for Dynamic Multi-scale Convolution for Dialect Identification
Figure 2 for Dynamic Multi-scale Convolution for Dialect Identification
Figure 3 for Dynamic Multi-scale Convolution for Dialect Identification
Figure 4 for Dynamic Multi-scale Convolution for Dialect Identification
Viaarxiv icon