How to Aggregate Acoustic Delta Features for Deep Speaker Embeddings.

Youngsam Kim Jong-Hyuk Roh Kwantae Cho Sangrae Cho

Published in: ICTC (2020)

Keyphrases

feature extraction
feature vectors
low level
prior knowledge
extracting features
machine learning
image features
semi supervised
dimensionality reduction
speech recognition
false positives
keypoints
extracted features
unsupervised feature learning