1.8k citations · 2k across the 4 of their papers we have counts for
5 papers · 1 filter
Unsupervised adversarial domain adaptation for acoustic scene classification
Shayan Gharib, Konstantinos Drossos, Emre Çakir +2
A general problem in acoustic scene classification task is the mismatched conditions between training and testing data, which significantly reduces the performance of the developed…
Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations
Alex Lamb, Jonathan Binas, Anirudh Goyal +4
Deep networks have achieved impressive results across a variety of important tasks. However a known weakness is a failure to perform well when evaluated on data which differ from t…
Twin Regularization for online speech recognition
Mirco Ravanelli, Dmitriy Serdyuk, Yoshua Bengio
Online speech recognition is crucial for developing natural human-machine interfaces. This modality, however, is significantly more challenging than off-line ASR, since real-time/l…
Towards end-to-end spoken language understanding
Dmitriy Serdyuk, Yongqiang Wang, Christian Fuegen +3
Spoken language understanding system is traditionally designed as a pipeline of a number of components. First, the audio signal is processed by an automatic speech recognizer for t…
MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation
Konstantinos Drossos, Stylianos Ioannis Mimilakis, Dmitriy Serdyuk +3
Monaural singing voice separation task focuses on the prediction of the singing voice from a single channel music mixture signal. Current state of the art (SOTA) results in monaura…