Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Haizhou Li

Haizhou Li

Self-Transriber: Few-shot Lyrics Transcription with Self-training

Nov 18, 2022
Xiaoxue Gao, Xianghu Yue, Haizhou Li

Figure 1 for Self-Transriber: Few-shot Lyrics Transcription with Self-training

Figure 2 for Self-Transriber: Few-shot Lyrics Transcription with Self-training

Figure 3 for Self-Transriber: Few-shot Lyrics Transcription with Self-training

Figure 4 for Self-Transriber: Few-shot Lyrics Transcription with Self-training

* 5 pages

Access Paper or Ask Questions

I4U System Description for NIST SRE'20 CTS Challenge

Nov 02, 2022
Kong Aik Lee, Tomi Kinnunen, Daniele Colibro, Claudio Vair, Andreas Nautsch, Hanwu Sun, Liang He, Tianyu Liang, Qiongqiong Wang, Mickael Rouvier, Pierre-Michel Bousquet, Rohan Kumar Das, Ignacio Viñals Bailo, Meng Liu, Héctor Deldago, Xuechen Liu, Md Sahidullah, Sandro Cumani, Boning Zhang, Koji Okabe, Hitoshi Yamamoto, Ruijie Tao, Haizhou Li, Alfonso Ortega Giménez, Longbiao Wang, Luis Buera

Figure 1 for I4U System Description for NIST SRE'20 CTS Challenge

Figure 2 for I4U System Description for NIST SRE'20 CTS Challenge

Figure 3 for I4U System Description for NIST SRE'20 CTS Challenge

Figure 4 for I4U System Description for NIST SRE'20 CTS Challenge

* SRE 2021, NIST Speaker Recognition Evaluation Workshop, CTS Speaker Recognition Challenge, 14-12 December 2021

Access Paper or Ask Questions

ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding Inpainting

Oct 31, 2022
Zexu Pan, Wupeng Wang, Marvin Borsdorf, Haizhou Li

Figure 1 for ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding Inpainting

Figure 2 for ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding Inpainting

Figure 3 for ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding Inpainting

Access Paper or Ask Questions

Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework

Oct 30, 2022
Yiming Chen, Yan Zhang, Bin Wang, Zuozhu Liu, Haizhou Li

Figure 1 for Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework

Figure 2 for Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework

Figure 3 for Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework

Figure 4 for Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework

* Accepted in EMNLP 2022 main conference

Access Paper or Ask Questions

token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text

Oct 30, 2022
Xianghu Yue, Junyi Ao, Xiaoxue Gao, Haizhou Li

Figure 1 for token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text

Figure 2 for token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text

Figure 3 for token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text

Figure 4 for token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text

* Submitted to ICASSP 2023

Access Paper or Ask Questions

FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation

Oct 29, 2022
Chen Zhang, Luis Fernando D'Haro, Qiquan Zhang, Thomas Friedrichs, Haizhou Li

Figure 1 for FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation

Figure 2 for FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation

Figure 3 for FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation

Figure 4 for FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation

* EMNLP-2022, 20 pages

Access Paper or Ask Questions

Speaker recognition with two-step multi-modal deep cleansing

Oct 28, 2022
Ruijie Tao, Kong Aik Lee, Zhan Shi, Haizhou Li

Figure 1 for Speaker recognition with two-step multi-modal deep cleansing

Figure 2 for Speaker recognition with two-step multi-modal deep cleansing

Figure 3 for Speaker recognition with two-step multi-modal deep cleansing

Figure 4 for Speaker recognition with two-step multi-modal deep cleansing

* 5 pages, 3 figures

Access Paper or Ask Questions