Vector-Based Feature Representations for Speech Signals: From Supervector to Latent Vector
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2020.3014559
Abstract: There are two basic types of feature representations for speech signals. The first type refers to probabilistic models, such as the Gaussian mixture model (GMM). The second type refers to vector-based feature representations, such as… read more here.
Keywords: vector; feature representations; vector based; representations speech ... See more keywords