183 citations · 234 across the 3 of their papers we have counts for
6 papers
Learning to Rank Microphones for Distant Speech Recognition
Samuele Cornell, Alessio Brutti, Marco Matassoni +1
Fully exploiting ad-hoc microphone networks for distant speech recognition is still an open issue. Empirical evidence shows that being able to select the best microphone leads to s…
Attention is All You Need in Speech Separation
Cem Subakan, Mirco Ravanelli, Samuele Cornell +2
Recurrent Neural Networks (RNNs) have long been the dominant architecture in sequence-to-sequence learning. RNNs, however, are inherently sequential models that do not allow parall…
LibriMix: An Open-Source Dataset for Generalizable Speech Separation
Joris Cosentino, Manuel Pariente, Samuele Cornell +2
In recent years, wsj0-2mix has become the reference dataset for single-channel speech separation. Most deep learning-based speech separation models today are benchmarked on it. How…
Asteroid: the PyTorch-based audio source separation toolkit for researchers
Manuel Pariente, Samuele Cornell, Joris Cosentino +11
This paper describes Asteroid, the PyTorch-based audio source separation toolkit for researchers. Inspired by the most successful neural source separation systems, it provides all…
The Speed Submission to DIHARD II: Contributions & Lessons Learned
Md Sahidullah, Jose Patino, Samuele Cornell +11
This paper describes the speaker diarization systems developed for the Second DIHARD Speech Diarization Challenge (DIHARD II) by the Speed team. Besides describing the system, whic…
Filterbank design for end-to-end speech separation
Manuel Pariente, Samuele Cornell, Antoine Deleforge +1
Single-channel speech separation has recently made great progress thanks to learned filterbanks as used in ConvTasNet. In parallel, parameterized filterbanks have been proposed for…