1 citations · 1 across the 4 of their papers we have counts for
4 papers · 1 filter
CrowdioSet and PaRIRset: Two Datasets Towards Live Music Source Separation
Enric Gusó, Xavier Serra
Most Music Source Separation (MSS) models do not generalize well to live music recordings because they are trained on studio recordings alone, disregarding the venue acoustics, the…
MB-RIRs: a Synthetic Room Impulse Response Dataset with Frequency-Dependent Absorption Coefficients
Enric Gusó, Joanna Luberadzka, Umut Sayin +1
We investigate the effects of four strategies for improving the ecological validity of synthetic room impulse response (RIR) datasets for monoaural Speech Enhancement (SE). We impl…
An objective evaluation of Hearing Aids and DNN-based speech enhancement in complex acoustic scenes
Enric Gusó, Joanna Luberadzka, Martí Baig +2
We investigate the objective performance of five high-end commercially available Hearing Aid (HA) devices compared to DNN-based speech enhancement algorithms in complex acoustic en…
On loss functions and evaluation metrics for music source separation
Enric Gusó, Jordi Pons, Santiago Pascual +1
We investigate which loss functions provide better separations via benchmarking an extensive set of those for music source separation. To that end, we first survey the most represe…