AI Chat AI Image Generator AI Video Text to Speech

Language-depedent I-Vectors for LRE15

09/29/2017

∙

by Niko Brümmer, et al.

∙

∙

A standard recipe for spoken language recognition is to apply a Gaussian back-end to i-vectors. This ignores the uncertainty in the i-vector extraction, which could be important especially for short utterances. A recent paper by Cumani, Plchot and Fer proposes a solution to propagate that uncertainty into the backend. We propose an alternative method of propagating the uncertainty.

Niko Brümmer
22 publications
Albert Swart
8 publications

page 1

page 2

page 3

page 4

research

∙ 04/04/2023

Thematic context vector association based on event uncertainty for Twitter

Keyword extraction is a crucial process in text mining. The extraction o...

5 Vaibhav Khatavkar, et al. ∙

research

∙ 09/09/2018

End-to-end Language Identification using NetFV and NetVLAD

In this paper, we apply the NetFV and NetVLAD layers for the end-to-end ...

0 Jinkun Chen, et al. ∙

research

∙ 10/16/2018

Deep neural network based i-vector mapping for speaker verification using short utterances

Text-independent speaker recognition using short utterances is a highly ...

0 Jinxi Guo, et al. ∙

research

∙ 07/13/2019

Speaker Recognition with Random Digit Strings Using Uncertainty Normalized HMM-based i-vectors

In this paper, we combine Hidden Markov Models (HMMs) with i-vector extr...

0 Nooshin Maghsoodi, et al. ∙

research

∙ 12/22/2014

Language Recognition using Random Indexing

Random Indexing is a simple implementation of Random Projections with a ...

0 Aditya Joshi, et al. ∙

research

∙ 10/27/2022

AmberNet: A Compact End-to-End Model for Spoken Language Identification

We present AmberNet, a compact end-to-end neural network for Spoken Lang...

0 Fei Jia, et al. ∙

research

∙ 02/26/2009

Dipole Vectors in Images Processing

Instead of evaluating the gradient field of the brightness map of an ima...

0 Amelia Sparavigna, et al. ∙