Login / Signup
Improvements on Deep Bottleneck Network based I-Vector Representation for Spoken Language Identification.
Yan Song
Ruilian Cui
Ian McLoughlin
Li-Rong Dai
Published in:
Odyssey (2016)
Keyphrases
</>
language identification
vector representation
fixed length
speaker identification
similarity measure
similarity computation
document representation
speech recognition
document images
broadcast news
semantic description
distance measure
image classification
data fusion
automatic speech recognition