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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Gil Keren

Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion


Apr 05, 2021
Duc Le, Mahaveer Jain, Gil Keren, Suyoun Kim, Yangyang Shi, Jay Mahadeokar, Julian Chan, Yuan Shangguan, Christian Fuegen, Ozlem Kalinli, Yatharth Saraf, Michael L. Seltzer

* Submitted to INTERSPEECH 2021 

  Access Paper or Ask Questions

Deep Shallow Fusion for RNN-T Personalization


Nov 16, 2020
Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer

* To appear at SLT 2021 

  Access Paper or Ask Questions

Alignment Restricted Streaming Recurrent Neural Network Transducer


Nov 05, 2020
Jay Mahadeokar, Yuan Shangguan, Duc Le, Gil Keren, Hang Su, Thong Le, Ching-Feng Yeh, Christian Fuegen, Michael L. Seltzer

* Accepted for presentation at IEEE Spoken Language Technology Workshop (SLT) 2021 

  Access Paper or Ask Questions

Contextual RNN-T For Open Domain ASR


Jun 04, 2020
Mahaveer Jain, Gil Keren, Jay Mahadeokar, Yatharth Saraf


  Access Paper or Ask Questions

Single-Channel Speech Separation with Auxiliary Speaker Embeddings


Jun 24, 2019
Shuo Liu, Gil Keren, Björn Schuller

* 5 pages including reference 

  Access Paper or Ask Questions

Scaling Speech Enhancement in Unseen Environments with Noise Embeddings


Oct 26, 2018
Gil Keren, Jing Han, Björn Schuller

* The Fifth CHiME Challenge Workshop, 2018 

  Access Paper or Ask Questions

Calibrated Prediction Intervals for Neural Network Regressors


Oct 26, 2018
Gil Keren, Nicholas Cummins, Björn Schuller

* IEEE Access (Volume 6), 2018 

  Access Paper or Ask Questions

Fast Single-Class Classification and the Principle of Logit Separation


Sep 17, 2018
Gil Keren, Sivan Sabato, Björn Schuller

* Published as a conference paper in ICDM 2018 

  Access Paper or Ask Questions

Weakly Supervised One-Shot Detection with Attention Similarity Networks


Jun 27, 2018
Gil Keren, Maximilian Schmitt, Thomas Kehrenberg, Björn Schuller


  Access Paper or Ask Questions

Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data


Jul 20, 2017
Gil Keren, Björn Schuller


  Access Paper or Ask Questions

Tunable Sensitivity to Large Errors in Neural Network Training


Nov 23, 2016
Gil Keren, Sivan Sabato, Björn Schuller

* The paper is accepted to the AAAI 2017 conference 

  Access Paper or Ask Questions