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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder


Feb 12, 2022
Bolaji Yusuf, Ankur Gandhe, Alex Sokolov

Add code

* 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (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

RescoreBERT: Discriminative Speech Recognition Rescoring with BERT


Feb 07, 2022
Liyan Xu, Yile Gu, Jari Kolehmainen, Haidar Khan, Ankur Gandhe, Ariya Rastrow, Andreas Stolcke, Ivan Bulyko

Add code

* 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

A Likelihood Ratio based Domain Adaptation Method for E2E Models


Jan 10, 2022
Chhavi Choudhury, Ankur Gandhe, Xiaohan Ding, Ivan Bulyko

Add code

* Submitted 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

Domain Prompts: Towards memory and compute efficient domain adaptation of ASR systems


Dec 16, 2021
Saket Dingliwal, Ashish Shenoy, Sravan Bodapati, Ankur Gandhe, Ravi Teja Gadde, Katrin Kirchhoff

Add code

* 4 pages ICASSP submission 

   Access Paper or Ask Questions

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

Lattention: Lattice-attention in ASR rescoring


Nov 19, 2021
Prabhat Pandey, Sergio Duarte Torres, Ali Orkan Bayer, Ankur Gandhe, Volker Leutnant

Add code

* Submitted 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

Prompt-tuning in ASR systems for efficient domain-adaptation


Oct 22, 2021
Saket Dingliwal, Ashish Shenoy, Sravan Bodapati, Ankur Gandhe, Ravi Teja Gadde, Katrin Kirchhoff

Add code

* WeCNLP 2021 camera-ready 

   Access Paper or Ask Questions

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

Efficient domain adaptation of language models in ASR systems using Prompt-tuning


Oct 13, 2021
Saket Dingliwal, Ashish Shenoy, Sravan Bodapati, Ankur Gandhe, Ravi Teja Gadde, Katrin Kirchhoff

Add code

* WeCNLP accepted version 

   Access Paper or Ask Questions

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

Attention-based Contextual Language Model Adaptation for Speech Recognition


Jun 02, 2021
Richard Diehl Martinez, Scott Novotney, Ivan Bulyko, Ariya Rastrow, Andreas Stolcke, Ankur Gandhe

Add code


   Access Paper or Ask Questions

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

Personalization Strategies for End-to-End Speech Recognition Systems


Feb 15, 2021
Aditya Gourav, Linda Liu, Ankur Gandhe, Yile Gu, Guitang Lan, Xiangyang Huang, Shashank Kalmane, Gautam Tiwari, Denis Filimonov, Ariya Rastrow, Andreas Stolcke, Ivan Bulyko

Add code

* 5 pages, 5 tables, 1 figure 

   Access Paper or Ask Questions

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

Domain-aware Neural Language Models for Speech Recognition


Jan 05, 2021
Linda Liu, Yile Gu, Aditya Gourav, Ankur Gandhe, Shashank Kalmane, Denis Filimonov, Ariya Rastrow, Ivan Bulyko

Add code

* language modeling, second-pass rescoring, domain adaptation, automatic speech recognition 

   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
>>