Picture for Yanpei Shi

Yanpei Shi

Swin-BERT: A Feature Fusion System designed for Speech-based Alzheimer's Dementia Detection

Add code
Oct 09, 2024
Viaarxiv icon

T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model

Add code
Oct 29, 2020
Figure 1 for T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model
Figure 2 for T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model
Figure 3 for T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model
Figure 4 for T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model
Viaarxiv icon

Speaker Re-identification with Speaker Dependent Speech Enhancement

Add code
May 15, 2020
Figure 1 for Speaker Re-identification with Speaker Dependent Speech Enhancement
Figure 2 for Speaker Re-identification with Speaker Dependent Speech Enhancement
Figure 3 for Speaker Re-identification with Speaker Dependent Speech Enhancement
Figure 4 for Speaker Re-identification with Speaker Dependent Speech Enhancement
Viaarxiv icon

Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification

Add code
May 15, 2020
Figure 1 for Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
Figure 2 for Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
Figure 3 for Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
Figure 4 for Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
Viaarxiv icon

Supervised Speaker Embedding De-Mixing in Two-Speaker Environment

Add code
Jan 14, 2020
Figure 1 for Supervised Speaker Embedding De-Mixing in Two-Speaker Environment
Figure 2 for Supervised Speaker Embedding De-Mixing in Two-Speaker Environment
Figure 3 for Supervised Speaker Embedding De-Mixing in Two-Speaker Environment
Figure 4 for Supervised Speaker Embedding De-Mixing in Two-Speaker Environment
Viaarxiv icon

Robust Speaker Recognition Using Speech Enhancement And Attention Model

Add code
Jan 14, 2020
Figure 1 for Robust Speaker Recognition Using Speech Enhancement And Attention Model
Figure 2 for Robust Speaker Recognition Using Speech Enhancement And Attention Model
Figure 3 for Robust Speaker Recognition Using Speech Enhancement And Attention Model
Figure 4 for Robust Speaker Recognition Using Speech Enhancement And Attention Model
Viaarxiv icon

H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model

Add code
Oct 19, 2019
Figure 1 for H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
Figure 2 for H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
Figure 3 for H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
Figure 4 for H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
Viaarxiv icon

Contextual Joint Factor Acoustic Embeddings

Add code
Oct 16, 2019
Figure 1 for Contextual Joint Factor Acoustic Embeddings
Figure 2 for Contextual Joint Factor Acoustic Embeddings
Figure 3 for Contextual Joint Factor Acoustic Embeddings
Figure 4 for Contextual Joint Factor Acoustic Embeddings
Viaarxiv icon

Improving Robustness In Speaker Identification Using A Two-Stage Attention Model

Add code
Sep 24, 2019
Figure 1 for Improving Robustness In Speaker Identification Using A Two-Stage Attention Model
Figure 2 for Improving Robustness In Speaker Identification Using A Two-Stage Attention Model
Figure 3 for Improving Robustness In Speaker Identification Using A Two-Stage Attention Model
Figure 4 for Improving Robustness In Speaker Identification Using A Two-Stage Attention Model
Viaarxiv icon