Estefanía Cano — accepted AI-conference papers

2021

Language-Sensitive Music Emotion Recognition Models: are We Really There Yet?

Juan Sebastián Gómez Cañón, Estefanía Cano, Ana Gabriela Pandrea, Perfecto Herrera, Emilia Gómez

ICASSP 2021accepted

Our previous research showed promising results when transferring features learned from speech to train emotion recognition models for music. In this context, we implemented a denoising autoencoder as a pretraining approach to extract features from speech in two languages (English and Mandarin). From…

Cited by 0 Source ↗Scholar ↗

2018

The Dimensions of Perceptual Quality of Sound Source Separation

Estefanía Cano, Judith Liebetrau, Derry Fitzgerald, Karlheinz Brandenburg

ICASSP 2018accepted

Quality of sound source separation algorithms has traditionally been evaluated based on a set of established quality metrics: target distortion, interference from other sources, artifacts distortion, and a measure of overall separation quality. In our previous work, listening test results were prese…

Cited by 0 Source ↗Scholar ↗