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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities


Jul 22, 2022
Pranav Dheram, Murugesan Ramakrishnan, Anirudh Raju, I-Fan Chen, Brian King, Katherine Powell, Melissa Saboowala, Karan Shetty, Andreas Stolcke

* Proc. Interspeech 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation


Jul 16, 2022
Viet Anh Trinh, Pegah Ghahremani, Brian King, Jasha Droppo, Andreas Stolcke, Roland Maas

* Accepted for publication at Interspeech 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Adversarial Reweighting for Speaker Verification Fairness


Jul 15, 2022
Minho Jin, Chelsea J. -T. Ju, Zeya Chen, Yi-Chieh Liu, Jasha Droppo, Andreas Stolcke


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Graph-based Multi-View Fusion and Local Adaptation: Mitigating Within-Household Confusability for Speaker Identification


Jul 08, 2022
Long Chen, Yixiong Meng, Venkatesh Ravichandran, Andreas Stolcke

* To appear in Interspeech 2022. arXiv admin note: text overlap with arXiv:2106.08207 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signals


Mar 16, 2022
Scott Novotney, Sreeparna Mukherjee, Zeeshan Ahmed, Andreas Stolcke

* To appear in Findings of ACL 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer


Feb 24, 2022
Kishan K C, Zhenning Tan, Long Chen, Minho Jin, Eunjung Han, Andreas Stolcke, Chul Lee

* To appear in Proc. IEEE ICASSP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Improving fairness in speaker verification via Group-adapted Fusion Network


Feb 23, 2022
Hua Shen, Yuguang Yang, Guoli Sun, Ryan Langman, Eunjung Han, Jasha Droppo, Andreas Stolcke

* To appear in Proc. IEEE ICASSP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Contrastive-mixup learning for improved speaker verification


Feb 22, 2022
Xin Zhang, Minho Jin, Roger Cheng, Ruirui Li, Eunjung Han, Andreas Stolcke


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition


Feb 17, 2022
Chao-Han Huck Yang, Zeeshan Ahmed, Yile Gu, Joseph Szurley, Roger Ren, Linda Liu, Andreas Stolcke, Ivan Bulyko

* Accepted to ICASSP 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Self-supervised Speaker Recognition Training Using Human-Machine Dialogues


Feb 07, 2022
Metehan Cekic, Ruirui Li, Zeya Chen, Yuguang Yang, Andreas Stolcke, Upamanyu Madhow

* 5 pages, 2 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>