Modeling phrasing and prominence using deep recurrent learningAndrew RosenbergRaul Fernandezet al.2015INTERSPEECH 2015Conference paper
The RedDots data collection for speaker recognitionK.A. LeeA. Larcheret al.2015INTERSPEECH 2015Conference paper
CapCap: An output-agreement game for video captioningHernisa KacorriKaoru Shinkawaet al.2015INTERSPEECH 2015Conference paper
Deep neural network training emphasizing central framesGakuto KurataDaniel Willett2015INTERSPEECH 2015Conference paper
A multi-region deep neural network model in speech recognitionJia CuiGeorge Saonet al.2015INTERSPEECH 2015Conference paper