Kurdish Spoken Dialect Recognition Using X-Vector Speaker Embedding.

Arash Amani Mohammad MohammadAmini Hadi Veisi

Published in: SPECOM (2021)

Keyphrases

speech recognition
vector space
automatic speech recognition
feature vectors
hidden markov models
language model
audio visual
induction motor
spoken words
vector data
speaker verification
broadcast news
multi modal
nonlinear dimensionality reduction
neural network
speaker dependent
data sets