Exploring the role of phonetic bottleneck features for speaker and language recognition
ICASSP, pp. 5575-5579, 2016.
Using bottleneck features extracted from a deep neural network (DNN) trained to predict senone posteriors has resulted in new, state-of-the-art technology for language and speaker identification. For language identification, the featuresu0027 dense phonetic information is believed to enable improved performance by better representing lang...More
Full Text (Upload PDF)
PPT (Upload PPT)