activity
20192025
most citedSpeechBrain: A General-Purpose Speech Toolkit

514 citations · 751 across the 10 of their papers we have counts for

collaborators
Showing eess.ASShow all

9 papers · 1 filter

eess.AS20222 cited

Conversational Speech Separation: an Evaluation Study for Streaming Applications

Giovanni Morrone, Samuele Cornell, Enrico Zovato +2

Continuous speech separation (CSS) is a recently proposed framework which aims at separating each speaker from an input mixture signal in a streaming fashion. Hereafter we perform…

eess.AS2022

Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge

Yen-Ju Lu, Samuele Cornell, Xuankai Chang +5

This paper describes our submission to the L3DAS22 Challenge Task 1, which consists of speech enhancement with 3D Ambisonic microphones. The core of our approach combines Deep Neur…

eess.AS2021

REAL-M: Towards Speech Separation on Real Mixtures

Cem Subakan, Mirco Ravanelli, Samuele Cornell +1

In recent years, deep learning based source separation has achieved impressive results. Most studies, however, still evaluate separation models on synthetic datasets, while the per…

eess.AS2021514 cited

SpeechBrain: A General-Purpose Speech Toolkit

Mirco Ravanelli, Titouan Parcollet, Peter Plantinga +18

SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to facilitate the research and development of neural speech processing technologies by being simple, fle…

eess.AS2021

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…

eess.AS2020

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…