Alert button
Picture for Lantian Li

Lantian Li

Alert button

How phonemes contribute to deep speaker models?

Feb 05, 2024
Pengqi Li, Tianhao Wang, Lantian Li, Askar Hamdulla, Dong Wang

Viaarxiv icon

Adversarial Data Augmentation for Robust Speaker Verification

Feb 05, 2024
Zhenyu Zhou, Junhui Chen, Namin Wang, Lantian Li, Dong Wang

Viaarxiv icon

A Glance is Enough: Extract Target Sentence By Looking at A keyword

Oct 09, 2023
Ying Shi, Dong Wang, Lantian Li, Jiqing Han

Figure 1 for A Glance is Enough: Extract Target Sentence By Looking at A keyword
Figure 2 for A Glance is Enough: Extract Target Sentence By Looking at A keyword
Figure 3 for A Glance is Enough: Extract Target Sentence By Looking at A keyword
Figure 4 for A Glance is Enough: Extract Target Sentence By Looking at A keyword
Viaarxiv icon

An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition

Sep 25, 2023
Zhenyu Zhou, Junhui Chen, Namin Wang, Lantian Li, Dong Wang

Figure 1 for An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition
Figure 2 for An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition
Figure 3 for An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition
Viaarxiv icon

Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification

Sep 25, 2023
Wan Lin, Lantian Li, Dong Wang

Figure 1 for Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification
Figure 2 for Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification
Figure 3 for Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification
Figure 4 for Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification
Viaarxiv icon

Spot keywords from very noisy and mixed speech

May 28, 2023
Ying Shi, Dong Wang, Lantian Li, Jiqing Han, Shi Yin

Figure 1 for Spot keywords from very noisy and mixed speech
Figure 2 for Spot keywords from very noisy and mixed speech
Figure 3 for Spot keywords from very noisy and mixed speech
Figure 4 for Spot keywords from very noisy and mixed speech
Viaarxiv icon

A Multi-Scale Attentive Transformer for Multi-Instrument Symbolic Music Generation

May 26, 2023
Xipin Wei, Junhui Chen, Zirui Zheng, Li Guo, Lantian Li, Dong Wang

Figure 1 for A Multi-Scale Attentive Transformer for Multi-Instrument Symbolic Music Generation
Figure 2 for A Multi-Scale Attentive Transformer for Multi-Instrument Symbolic Music Generation
Figure 3 for A Multi-Scale Attentive Transformer for Multi-Instrument Symbolic Music Generation
Figure 4 for A Multi-Scale Attentive Transformer for Multi-Instrument Symbolic Music Generation
Viaarxiv icon

Visualizing data augmentation in deep speaker recognition

May 25, 2023
Pengqi Li, Lantian Li, Askar Hamdulla, Dong Wang

Figure 1 for Visualizing data augmentation in deep speaker recognition
Figure 2 for Visualizing data augmentation in deep speaker recognition
Figure 3 for Visualizing data augmentation in deep speaker recognition
Figure 4 for Visualizing data augmentation in deep speaker recognition
Viaarxiv icon

CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition

May 25, 2023
Lantian Li, Xiaolou Li, Haoyu Jiang, Chen Chen, Ruihai Hou, Dong Wang

Figure 1 for CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition
Figure 2 for CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition
Figure 3 for CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition
Figure 4 for CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition
Viaarxiv icon

Ordered and Binary Speaker Embedding

May 25, 2023
Jiaying Wang, Xianglong Wang, Namin Wang, Lantian Li, Dong Wang

Figure 1 for Ordered and Binary Speaker Embedding
Figure 2 for Ordered and Binary Speaker Embedding
Figure 3 for Ordered and Binary Speaker Embedding
Figure 4 for Ordered and Binary Speaker Embedding
Viaarxiv icon