The Use of Voice Source Features for Sung Speech Recognition.

Gerardo Roa Dabike Jon Barker

Published in: CoRR (2021)

Keyphrases

speech recognition
speech recognition systems
speech processing
hidden markov models
speech synthesis
language model
speech recognition errors
mel frequency cepstral coefficients
pattern recognition

cepstral coefficients
speech understanding
voice activity detection
speaker identification
automatic speech recognition
speech recognition technology
speech signal
keyword spotting
feature set

low level
speaker independent
noisy environments
extracting features
machine learning
signal processing
classification accuracy
feature vectors
vocal tract

hybrid method
extracted features
non stationary
speaker dependent
speech retrieval
computer vision
speech recognizers
information retrieval