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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Error-aware Quantization through Noise Tempering


Dec 11, 2022
Zheng Wang, Juncheng B Li, Shuhui Qu, Florian Metze, Emma Strubell

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

Normalized Contrastive Learning for Text-Video Retrieval


Nov 30, 2022
Yookoon Park, Mahmoud Azab, Bo Xiong, Seungwhan Moon, Florian Metze, Gourab Kundu, Kirmani Ahmed

Add code

* Published in EMNLP 2022 

   Access Paper or Ask Questions

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

Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models


Oct 27, 2022
Siddhant Arora, Siddharth Dalmia, Brian Yan, Florian Metze, Alan W Black, Shinji Watanabe

Add code

* Accepted at EMNLP 2022 Findings. Our code and models will be publicly available as part of the ESPnet-SLU toolkit: https://github.com/espnet/espnet and the release can be followed here: https://github.com/espnet/espnet/pull/4735 

   Access Paper or Ask Questions

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

SQuAT: Sharpness- and Quantization-Aware Training for BERT


Oct 13, 2022
Zheng Wang, Juncheng B Li, Shuhui Qu, Florian Metze, Emma Strubell

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

CTC Alignments Improve Autoregressive Translation


Oct 11, 2022
Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W Black, Shinji Watanabe

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

ASR2K: Speech Recognition for Around 2000 Languages without Audio


Sep 06, 2022
Xinjian Li, Florian Metze, David R Mortensen, Alan W Black, Shinji Watanabe

Add code

* 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

Masked Autoencoders that Listen


Jul 13, 2022
Po-Yao, Huang, Hu Xu, Juncheng Li, Alexei Baevski, Michael Auli, Wojciech Galuba, Florian Metze, Christoph Feichtenhofer

Add code

* Technical report 

   Access Paper or Ask Questions

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

LegoNN: Building Modular Encoder-Decoder Models


Jun 07, 2022
Siddharth Dalmia, Dmytro Okhonko, Mike Lewis, Sergey Edunov, Shinji Watanabe, Florian Metze, Luke Zettlemoyer, Abdelrahman Mohamed

Add code

* 13 pages; Submitted to TASLP 2022 

   Access Paper or Ask Questions

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

On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization


May 24, 2022
Shruti Palaskar, Akshita Bhagia, Yonatan Bisk, Florian Metze, Alan W Black, Ana Marasovic

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

Robustness of Neural Architectures for Audio Event Detection


May 06, 2022
Juncheng B Li, Shuhui Qu, Florian Metze

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
1
2
3
4
5
6
7
>>