activity
20172026
most citedSpeechBrain: A General-Purpose Speech Toolkit

514 citations · 566 across the 62 of their papers we have counts for

collaborators
Showing 2017Show all

8 papers · 1 filter

cs.CL2017

Deep Learning for Distant Speech Recognition

Mirco Ravanelli

Deep learning is an emerging technology that is considered one of the most promising directions for reaching higher levels of artificial intelligence. Among the other achievements,…

eess.AS2017

Realistic multi-microphone data simulation for distant speech recognition

Mirco Ravanelli, Piergiorgio Svaizer, Maurizio Omologo

The availability of realistic simulated corpora is of key importance for the future progress of distant speech recognition technology. The reliability, flexibility and low computat…

eess.AS20173 cited

Audio Concept Classification with Hierarchical Deep Neural Networks

Mirco Ravanelli, Benjamin Elizalde, Karl Ni +1

Audio-based multimedia retrieval tasks may identify semantic information in audio streams, i.e., audio concepts (such as music, laughter, or a revving engine). Conventional Gaussia…

eess.AS20176 cited

Contaminated speech training methods for robust DNN-HMM distant speech recognition

Mirco Ravanelli, Maurizio Omologo

Despite the significant progress made in the last years, state-of-the-art speech recognition technologies provide a satisfactory performance only in the close-talking condition. Ro…

eess.AS20171 cited

The DIRHA-English corpus and related tasks for distant-speech recognition in domestic environments

Mirco Ravanelli, Maurizio Omologo

This paper introduces the contents and the possible usage of the DIRHA-ENGLISH multi-microphone corpus, recently realized under the EC DIRHA project. The reference scenario is a do…

cs.CL2017

Improving speech recognition by revising gated recurrent units

Mirco Ravanelli, Philemon Brakel, Maurizio Omologo +1

Speech recognition is largely taking advantage of deep learning, showing that substantial benefits can be obtained by modern Recurrent Neural Networks (RNNs). The most popular RNNs…