Gil Keren

发表

Scaling Speech Enhancement in Unseen Environments with Noise Embeddings pdf

Björn W. Schuller, Jing Han, Gil Keren, 2018, ArXiv.

Single-Channel Speech Separation with Auxiliary Speaker Embeddings pdf

Gil Keren, Shuo Liu, Bjorn Schuller, 2019, ArXiv.

A Walkthrough for the Principle of Logit Separation

Björn W. Schuller, Gil Keren, Sivan Sabato, 2019, IJCAI.

Deep Shallow Fusion for RNN-T Personalization pdf

Gil Keren, Jay Mahadeokar, Christian Fuegen, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

CAST a database: Rapid targeted large-scale big data acquisition via small-world modelling of social media platforms

Björn W. Schuller, Gil Keren, Nicholas Cummins, 2017, 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII).

Tunable Sensitivity to Large Errors in Neural Network Training pdf

Björn W. Schuller, Gil Keren, Sivan Sabato, 2017, AAAI.

Convolutional RNN: An enhanced model for extracting features from sequential data

Björn W. Schuller, Gil Keren, Björn Schuller, 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

N-HANS: Introducing the Augsburg Neuro-Holistic Audio-eNhancement System pdf

Gil Keren, Shuo Liu, Bjorn Schuller, 2019, ArXiv.

Neural Network Supervision: Notes on Loss Functions, Labels and Confidence Estimation

Gil Keren, 2020 .

The Principle of Logit Separation

Björn Schuller, Gil Keren, Sivan Sabato, 2018 .

Calibrated Prediction Intervals for Neural Network Regressors

Björn Schuller, Gil Keren, Nicholas Cummins, 2018, IEEE Access.

End-to-end learning for dimensional emotion recognition from physiological signals

Fabien Ringeval, Erik Marchi, Björn W. Schuller, 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).

Towards Robust Speech Emotion Recognition Using Deep Residual Networks for Speech Enhancement

Björn Schuller, Gil Keren, Johannes Wagner, 2019, INTERSPEECH.

Deep learning for multisensorial and multimodal interaction

Stefanos Zafeiriou, Björn Schuller, Gil Keren, 2018, The Handbook of Multimodal-Multisensor Interfaces, Volume 2.

On Definable Skolem Functions in Weakly O-Minimal nonvaluational Structures

Gil Keren, Pantelis E. Eleftheriou, Assaf Hasson, 2017, J. Symb. Log..

Convolutional Neural Networks with Data Augmentation for Classifying Speakers' Native Language

Björn W. Schuller, Gil Keren, Jun Deng, 2016, INTERSPEECH.

Analysis of loss functions for fast single-class classification

Björn Schuller, Gil Keren, Sivan Sabato, 2019, Knowledge and Information Systems.

Contextual RNN-T For Open Domain ASR pdf

Gil Keren, Yatharth Saraf, Jay Mahadeokar, 2020, INTERSPEECH.

Weakly Supervised One-Shot Detection with Attention Siamese Networks pdf

Björn W. Schuller, Gil Keren, Maximilian Schmitt, 2018, ArXiv.

Alignment Restricted Streaming Recurrent Neural Network Transducer pdf

Hang Su, Gil Keren, Jay Mahadeokar, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

Fast Single-Class Classification and the Principle of Logit Separation

Björn W. Schuller, Gil Keren, Sivan Sabato, 2017, 2018 IEEE International Conference on Data Mining (ICDM).

N-HANS: A neural network-based toolkit for in-the-wild audio enhancement

Björn Schuller, Gil Keren, Emilia Parada-Cabaleiro, 2021, Multim. Tools Appl..

A Time-Domain Convolutional Recurrent Network for Packet Loss Concealment

Gil Keren, Didi Zhang, Kaustubh Kalgaonkar, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Alignment Restricted Streaming Recurrent Neural Network Transducer

Gil Keren, Ching-Feng Yeh, Duc Le, 2021, 2021 IEEE Spoken Language Technology Workshop (SLT).

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

Gil Keren, Julian Chan, Yatharth Saraf, 2021, Interspeech 2021.

Scaling ASR Improves Zero and Few Shot Learning pdf

Gil Keren, Frank Zhang, Ozlem Kalinli, 2021, INTERSPEECH.

Emotion Recognition in Speech with Latent Discriminative Representations Learning

Björn Schuller, Zixing Zhang, Gil Keren, 2018, Acta Acustica united with Acustica.

Weakly Supervised One-Shot Detection with Attention Similarity Networks

Gil Keren, Maximilian Schmitt, Thomas Kehrenberg, 2018 .