Picture for Romain Serizel

Romain Serizel

MULTISPEECH

Fast and efficient speech enhancement with variational autoencoders

Nov 02, 2022
Mostafa Sadeghi, Romain Serizel

Figure 1 for Fast and efficient speech enhancement with variational autoencoders

Access Paper or Ask Questions

Weighted variance variational autoencoder for speech enhancement

Nov 02, 2022
Ali Golmakani, Mostafa Sadeghi, Xavier Alameda-Pineda, Romain Serizel

Figure 1 for Weighted variance variational autoencoder for speech enhancement

Figure 2 for Weighted variance variational autoencoder for speech enhancement

Access Paper or Ask Questions

Audio-visual speech enhancement with a deep Kalman filter generative model

Nov 02, 2022
Ali Golmakani, Mostafa Sadeghi, Romain Serizel

Figure 1 for Audio-visual speech enhancement with a deep Kalman filter generative model

Figure 2 for Audio-visual speech enhancement with a deep Kalman filter generative model

Figure 3 for Audio-visual speech enhancement with a deep Kalman filter generative model

Access Paper or Ask Questions

How to Leverage DNN-based speech enhancement for multi-channel speaker verification?

Oct 17, 2022
Sandipana Dowerah, Romain Serizel, Denis Jouvet, Mohammad Mohammadamini, Driss Matrouf

Figure 1 for How to Leverage DNN-based speech enhancement for multi-channel speaker verification?

* 4th International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI' 2022), Oct 2022, Corfu, Greece

Access Paper or Ask Questions

A benchmark of state-of-the-art sound event detection systems evaluated on synthetic soundscapes

Feb 08, 2022
Francesca Ronchini, Romain Serizel

Figure 1 for A benchmark of state-of-the-art sound event detection systems evaluated on synthetic soundscapes

Figure 2 for A benchmark of state-of-the-art sound event detection systems evaluated on synthetic soundscapes

Figure 3 for A benchmark of state-of-the-art sound event detection systems evaluated on synthetic soundscapes

Figure 4 for A benchmark of state-of-the-art sound event detection systems evaluated on synthetic soundscapes

Access Paper or Ask Questions

Threshold Independent Evaluation of Sound Event Detection Scores

Jan 31, 2022
Janek Ebbers, Romain Serizel, Reinhold Haeb-Umbach

Figure 1 for Threshold Independent Evaluation of Sound Event Detection Scores

Figure 2 for Threshold Independent Evaluation of Sound Event Detection Scores

Figure 3 for Threshold Independent Evaluation of Sound Event Detection Scores

Figure 4 for Threshold Independent Evaluation of Sound Event Detection Scores

* accepted for ICASSP 2022

Access Paper or Ask Questions

Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes

Jun 15, 2021
Nicolas Furnon, Romain Serizel, Slim Essid, Irina Illina

Figure 1 for Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes

Figure 2 for Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes

Figure 3 for Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes

Figure 4 for Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes

* European Signal Processing Conference (EUSIPCO), IEEE, Aug 2021, Dublin, Ireland

Access Paper or Ask Questions