VTS feature compensation based on two-layer GMM structure for robust speech recognition.

Lin Zhou Haijing Li Ying Chen Zhenyang Wu Yong Lu

Published in: WCSP (2016)

Keyphrases

speech recognition
speaker identification
noisy environments
speech signal
speaker recognition
hidden markov models
language model
automatic speech recognition

speech processing
cepstral coefficients
speech synthesis
speech recognition technology
speech understanding
gaussian mixture model
voice activity detection

pattern recognition
speech recognizer
speech recognition systems
speaker independent
speech retrieval
speech recognizers
isolated word

machine learning
feature vectors
mel frequency cepstral coefficients
speaker adaptation
computer vision
speech recognition errors
information retrieval